US7805706B1 - Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers - Google Patents
Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers Download PDFInfo
- Publication number
- US7805706B1 US7805706B1 US11/157,395 US15739505A US7805706B1 US 7805706 B1 US7805706 B1 US 7805706B1 US 15739505 A US15739505 A US 15739505A US 7805706 B1 US7805706 B1 US 7805706B1
- Authority
- US
- United States
- Prior art keywords
- memory
- server
- erp
- database
- sap
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3471—Address tracing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
- G06F11/3428—Benchmarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/80—Database-specific techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/815—Virtual
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/87—Monitoring of transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/885—Monitoring specific for caches
Definitions
- ERP Enterprise Resource Planning
- the present process focuses on the software layer, which consists of the operating system (OS), an Enterprise Resource Planning (ERP) application SAP, and Database Management System (DBMS) software.
- OS operating system
- ERP Enterprise Resource Planning
- DBMS Database Management System
- Devised herein is a process with proven tuning techniques to optimize an ERP application SAP for better performance on multiprocessor servers in a three-tier client/server implementation.
- the focus is only on the software components. This process takes into consideration the Operating System (OS), the SAP application and the Database Management System (DBMS) software. It identifies the potential tuning opportunities for each of those software components.
- OS Operating System
- SAP SAP application
- DBMS Database Management System
- the process considers each component and evaluates its potential tuning opportunities. For each component, the process further identifies the subcomponents for potential tuning opportunities. For example, after identifying the OS, the process also evaluates the type of OS and the drivers that are supported on that OS.
- the process is thus reiterated through all the software components to identify each tuning opportunity and apply tuning techniques to derive at the optimal result. Once all the opportunities are identified and all the tuning techniques are applied, the process is deemed completed. Once the process is completed, optimal performance is achieved and bottlenecks and poor performance is thus avoided.
- FIG. 1 depicts the entire SAP Sales and Distribution (SD) three-tier benchmark implementation.
- FIG. 2 illustrates the first step in the process, which is to identify the software components.
- FIG. 3 illustrates the second step in the process, which is to identify tuning opportunities for the Operating System (OS) components and its subcomponents.
- This step includes the OS selection, device driver selection, memory management, and Direct I/O Bridge (DIB) to subpod mapping.
- DIB Direct I/O Bridge
- FIG. 4 illustrates the third step in the process, which is to identify tuning opportunities in the SAP application component and its subcomponents.
- This step includes SAP memory management, how to configure the SAP work process type and amount, SAP processor affinity, table buffering, and number range buffering.
- FIG. 5 shown as 5 A and 5 B, illustrates the last step in the process, which is to identify tuning opportunities in the Database Management System (DBMS) software component and its subcomponents.
- This step includes SQL Server memory management, SQL Server processor affinity, configuring lightweight threads or fibers, configuring the Windows threads, configuring the scheduling priority, configuring parallel query, configuring network connection affinity, SAP database configuration, and SAP database object configuration.
- SQL Server memory management SQL Server processor affinity
- configuring lightweight threads or fibers configuring the Windows threads
- configuring the scheduling priority configuring parallel query
- configuring network connection affinity SAP database configuration
- SAP database configuration SAP database object configuration
- FIG. 6 is a graph showing the benchmark results after applying the optimizing process on 16-, 24-, and 32-processor Unisys ES7000 systems.
- FIG. 7 illustrates a 16-CPU partition of a 32-bit ES70000 system.
- the partition consists of 4 subpods. Each subpod has 4 CPUs and a shared cache.
- FIG. 8 illustrates a 16-CPU partition of a 64-bit ES70000 system.
- the partition consists of 4 processor/memory modules.
- Each processor/memory module has 4 CPUs with its own memory.
- FIG. 9 demonstrates the Virtual Interface Architecture (VIA) network connection affinity for a 16-CPU server. It shows the network threads that handle connections from each application server running on a set of four CPUs using a predefined Virtual Interface Architecture (VIA) port.
- VIP Virtual Interface Architecture
- FIG. 1 depicts the entire SAP Sales and Distribution (SD) three-tier benchmark implementation.
- the implementation consists of one database server, multiple application servers, and multiple presentation servers. All servers are connected and communicate over a TCP/IP network.
- the application servers are connected to the database server through the high speed and high bandwidth Virtual Interface Architecture (VIA) network.
- VIP Virtual Interface Architecture
- the three-tier benchmark implementation includes a database server 30 , which is connected to a storage system 40 .
- the database server 30 communicates with a presentation server 10 and a group of application servers 20 a . . . 20 n via TCP/IP network, which is represented by a TCP/IP network cloud 16 .
- TCP/IP network which is represented by a TCP/IP network cloud 16 .
- the TCP/IP protocol allows all servers in the network to communicate and transmit data.
- the database server 30 communicates with the application servers 20 a . . . 20 n via a Virtual Interface Architecture (VIA), which is represented by a VIA network cloud 18 .
- the VIA communication protocol provides a high speed and high bandwidth communication between the database server 30 and the application servers 20 a . . . 20 n .
- a database server is running Microsoft SQL Server to provide database services.
- FIG. 2 depicts the software components in sequence for the multi-tier client/server environment. This is the first step in the sequence.
- the software components consist of the OS, SAP application, and DBMS. It is considered a large part in the multi-tier client/server implementation. Care must be exercised to ensure the “most bang for the buck” approach to software tuning.
- One way to achieve the best optimization is by following the best practices as described in this disclosure to evaluate and tune each component and its subcomponents so that the optimal performance is achieved and bottleneck is avoided.
- the first sequence in the process is to identify the software components and isolate each component into different categories including:
- the first process sequence is shown in FIG. 2 as a sequence of operations.
- the sequence starts at step 2 a and proceeds to operating system selection at step 2 b .
- the next step is the SAP application selection at step 2 c .
- step 2 d a selection is made for the Database Management System software, after which the sequence ends at step 2 e.
- the first process sequence identifies the software components. Once the software components are identified, tuning techniques can be applied to each components and their subcomponents in the later steps of the process. These tuning techniques are described later.
- FIG. 3 identifies the second process sequence which is to identify tuning opportunities in the OS level and its subcomponents. This step encompasses the following steps:
- OS Selection For the OS selection, consideration must be placed on the processor type i.e. 32-bit vs. 64-bit technology, the number of processors, the amount of memory, and hardware devices. Select an OS that supports either a 32-bit or 64-bit depending on the server technology. For example, Microsoft Windows OS family comes in different versions; each version supports a different type of server technology and requires a different amount of system resources. Select the OS that supports the hardware architecture and hardware resources in the computer system to ensure there are no compatibility issues and all hardware resources are fully utilized.
- Step 3 c The OS manages a hardware device through a device driver. Selecting the correct device drivers allows the OS to interface with the device effectively and avoid potential bottleneck and to improve overall system performance.
- DTB Direct I/O Bridge
- Subpod Submodule Mapping
- Step 3 e The OS handles I/O requests from any hardware devices through I/O interrupts.
- HBAs host bus adapters
- This technique is called DIB-to-subpod mapping.
- DIB-to-subpod mapping This technique improves I/O performance by keeping a process and its corresponding I/O interrupts together within the same subpod to take advantage of data localization because the data are located in the shared cache. As a result, system performance improves as the system latency, involved in cache coherency, is eliminated.
- step 3 a The second sequence in the process is shown in FIG. 3 .
- the sequence starts at step 3 a and proceeds to step 3 b , which requires a decision to select the OS. If the answer is “YES”, the sequence repeats at step 3 b . If the answer here is “NO”, which means no further OS selection tuning is required, the sequence then proceeds to step 3 c .
- step 3 c a decision to select a driver is made. If the answer is “YES”, then the sequence repeats at step 3 c until no further driver selection tuning is required. If the answer is “NO”, the sequence proceeds to step 3 d .
- step 3 d a decision to tune memory is made. If the answer is “YES”, repeat step 3 d until no more memory tuning is required.
- step 3 e The sequence then goes to step 3 e , which requires a decision whether to perform Direct I/O Bridge (DIB) to subpod mapping. If the answer is “YES”, repeat step 3 e until no more tuning is needed. If the answer is “NO”, proceed to step 3 f , where the sequence ends.
- DIB Direct I/O Bridge
- the OS For the OS selection in step 3 b of FIG. 3 , place consideration on selecting the right OS for the server technology and hardware resources.
- the OS comes in different versions and each version supports a minimum hardware resource requirement. Select the OS version the hardware can support, given the type of processors, the amount of physical memory in the server, and all hardware devices.
- Table I illustrates Windows Server 2003 editions and resources.
- a device driver often called driver, refers to the software used by the OS to manage a particular hardware device. Selecting the right driver is critical because it determines the performance of the hardware devices, which consequently affects the overall performance of the whole system.
- PAE Physical Address Extension
- an application process When an application process runs on the OS, it accesses memory space, which is a combination of physical memory and virtual memory. More memory is required when there are more applications, or processes, running on the server. In this case, the paging process increases dramatically and adversely affects the system performance. Applications can benefit from PAE because it provides more physical memory to a program. This reduces the need to swap the memory in the form of paging and in turn increases performance.
- a computer needs temporary space to store data during processing. As long as the physical memory is not fully consumed, the data can be stored in physical memory. However, as more applications are running, they consume more physical memory, and therefore need virtual memory beyond what is available in physical memory by using a part of the disk to temporary store information.
- Paging File Since information is moved to/from physical memory to disk in fixed size units called “Pages”, the file is referred to as “Page File”. Paging process refers to the way the system accesses paging files to store and retrieve data. Paging process can introduce poor performance, as accessing files from disks is slower than memory.
- PAE Whenever possible, enable PAE if the server has more than 4 GB of physical memory and an application can address memory larger than 4 GB. To enable PAE, use the /PAE switch in the boot.ini file.
- /3 GB Switch Typically, a process running under Windows 2000 or Windows 2003 32-bit can access up to 4 GB of memory address space with the combination of physical and virtual memory. By default, about 2 GB of this is reserved for the kernel or the OS, and about 2 GB is reserved for user mode programs or applications.
- the /3 GB switch allows the OS to allocate the virtual address space to give the user mode programs about 3 GB of space and limit the kernel to about 1 GB. In fact, the usable user mode program space is increased to 2.7 GB. Performance improves as user programs benefit from the additional space by using the /3 GB switch.
- Enable the /3 GB switch if there are several applications running on the server or that the application is memory intensive. To enable /3 GB, use the /3 GB switch in the boot.ini file. If the server has more than 16 GB of physical memory, do not use the /3 GB switch because the OS needs more than 1 GB for the kernel to manage a system with more than 16 GB of memory.
- this feature is specific to the 32-bit architecture as it uses the DIB-to-cluster low priority routing (LPR) interrupt binding format to pass DIB-to-cluster assignments to the hardware abstraction layer (HAL).
- LPR low priority routing
- DIB to subpod mapping For ES7000 32-bit technology, implement DIB to subpod mapping to direct I/O interrupts from a specific DIB to a subpod. By controlling I/O interrupts through the DIB to subpod mapping, system performance can be improved.
- DIB to subpod mapping in order to keep a process and its corresponding I/O interrupts together on the same subpod. This way, it can improve system performance because the data associated with the I/O operations are stored on the shared cache and thus eliminate the memory request latency time by accessing data across subpods.
- the third sequence in the process ( FIG. 4 ) is to identify tuning opportunities in the SAP application component and its subcomponents. How each component will be evaluated and tuned can be summarized as follows:
- FIG. 4 identifies the third sequence in the process.
- FIG. 4 starts at step 4 a and proceeds to step 4 b , where a decision whether to continue with memory allocation tuning is required. If the answer is “YES”, then the sequence repeats at step 4 b . If the answer to step 4 b is “NO”, the sequence proceeds to step 4 c .
- step 4 c a decision is made whether to define SAP work process type and amount. If the answer is “YES”, then repeat step 4 c . If the answer is “NO”, the sequence proceeds to step 4 d .
- step 4 d a decision is made whether to apply SAP processor affinity. If the answer is “YES”, repeat step 4 d . If the answer is “NO”, proceed to step 4 e .
- step 4 e a decision is made whether to buffer a table. If the answer is “YES”, repeat step 4 e . If the answer is “NO”, the sequence continues on to step 4 f where a decision is made whether to buffer the number range. If the answer is “YES”, then repeat step 4 f . If the answer is a “NO”, then the sequence ends at step 4 g.
- SAP Memory Management the memory must be given for SAP application processes to run effectively without starving other processes running on the same system.
- SAP R/3 application server contains one or more SAP instances.
- An instance is an administrative unit that combines SAP components that provide one or more services and can be started and stopped together. The instance usually contains more than one SAP work process. Each SAP work process requires a certain amount of memory to store data temporarily during run time.
- step 4 b There are two main memory areas in step 4 b for SAP processes, the memory area that is available exclusively to each work process, and the memory area that can be shared by all work processes in the same instance. When allocating the memory to a SAP application, both exclusive and shared memory areas must be configured.
- SAP and other applications such as file and print server services, are running on the same server, make sure sufficient memory is allocated to both applications so that they have enough memory to run effectively.
- Step 4 c of FIG. 4 Configure The SAP Work Process Type And Amount, consideration must be placed on the configuration of SAP work processes.
- SAP work processes perform unique functions.
- a dialog work process handles an interactive job; an update work process handles database update; a lock management work process handles locking at the SAP application level; a background work process handles background jobs processing; a spool work process handles printing services; a message server work process handles the communication between dispatchers; and a gateway work process handles the communication with the external system.
- Step 4 d of FIG. 4 SAP Processor Affinity, the ability to assign SAP work processes to run on specific processors is called processor affinity.
- Processor affinity improves overall system performance because SAP processes share the data residing on the shared cache among groups of processors and thereby minimize system latency.
- SAP automatically assigns SAP work processes to run on any CPU in the system.
- Each SAP instance has a shared memory area where all SAP work processes can share. Therefore, if multiple instances are running on a system, it is best to group SAP work processes of the same instance together in such a way that the processes can have access to the shared memory area as efficiently as possible.
- each processor sub-module is a set of four CPUs with its own shared cache, as seen in FIG. 7 .
- the shared cache allows processors to minimize memory latency and reduce contention for scarce bandwidth to and from memory by keeping accesses as close to the processor as possible, thus enabling faster accesses with fewer global system resource consumptions.
- shared cache When shared cache is used, data pages and instruction modules are located next to the processors that use them, in the fastest available form of memory.
- a group of four processors and memory is called a processor/memory module, as seen in FIG. 8 .
- Apply the same tuning technique as 32-bit system by assigning SAP work processes of an instance to the CPUs in the same processor/memory module.
- Using the CPUs located in the same processor/memory module allows the SAP work processes to share the same local memory and reduce the memory request latency time to access the memory across different processor/memory modules and this in turn will minimize memory latency and reduce system level bottlenecks.
- a good strategy is to balance SAP work processes across all the CPUs. For example, if a 16-processor system has four SAP instances running and each instance handles approximately the same amount of workload, assign each instance to run individually on 4 CPUs.
- a SAP instance consists of a set of processes that can be started and stopped together. For example, a SAP dialog instance, which is responsible for handling interactive user workload, contains two dialog work processes, and a dispatcher process.
- Table Buffering table buffering technique allows an SAP application to access the data from a local memory of the application server instead of going to the database. This improves the performance significantly because the database access time is a lot longer than the access time of local memory.
- table buffering minimizes database server load and avoids blocking of a SAP work process, as the work processes must wait for the data to be retrieved from the database before proceeding.
- SAP has a buffer synchronization mechanism in order to ensure that all SAP buffers across all SAP instances see the newly updated data on the database. Since the updated record introduces some overhead for invalidation and synchronization of buffered tables, table buffering should not be used for frequently updated tables.
- Number Range Buffering allows users to implement buffering mechanisms for SAP number range objects. If no buffering is implemented, performance bottleneck may occur at high volume of workload because only one process can have access to the number range objects at a time.
- Number range buffering technique is an option to buffer the number ranges in the SAP system. An advantage offered by buffering a number range is the increase in performance, since parallel processes can avoid lock/wait at the database level during number range assignment.
- the number range is temporarily stored on the database table, called NRIV_LOKAL.
- the number range and SAP instance number are used as part of a key.
- the performance is improved because the lock/wait problem is reduced.
- the advantage is that the number allocation is almost gap-free.
- the number may be assigned in a non-consecutive sequence.
- the drawback is that locks still occur within an instance. If high throughput is required, it is necessary to have users simultaneously work on many SAP instances.
- the number range is temporarily stored on the database table, called NRIV_LOKAL.
- the number range, SAP instance number, and work process number are used as part of a key.
- the lock/wait problem is eliminated.
- the number range allocation is almost gap-free. However, the number may be assigned in a non-consecutive sequence.
- the SAP application component is optimized and the performance bottleneck is thus avoided.
- FIGS. 5A and 5B The last sequence in the process is shown in FIGS. 5A and 5B .
- This sequence identifies tuning opportunities in the Database Management System software (DBMS) component and its subcomponents. How each component will be evaluated and tuned can be summarized as follows:
- each user-mode scheduler uses a single thread to control the scheduling of work requests on fibers.
- the number of fibers is controlled by the max worker threads parameter in SQL Server.
- step 5 a the sequence starts at step 5 a and proceeds to step 5 b which requires a decision whether to apply memory management tuning technique. If the answer is “YES”, then the sequence repeats at step 5 b to manage the memory. If the answer is “NO”, the sequence proceeds to step 5 c , which requires a decision whether to apply SQL processor affinity tuning. If the answer is “YES”, then the sequence repeats at step 5 c . If the answer is “NO” then proceeds to step 5 d , which requires a decision whether to apply SQL lightweight pooling tuning. If the answer is “YES”, then step 5 d is repeated. If the answer is “NO”, then proceeds to step 5 e . Step 5 e requires a decision whether to configure the Windows threads.
- step 5 e If the answer is “YES”, step 5 e is repeated. If the answer is “NO”, then it proceeds to step 5 f . Step 5 f requires a decision whether to configure scheduling priority. If the answer is “YES”, step 5 f is repeated. If the answer is “NO”, then the process continues to marker A over to FIG. 5B .
- step 5 g requires a decision whether to enable SQL parallel query option. If the answer is “YES”, then step 5 g is repeated. If the answer is “NO”, the sequence proceeds to step 5 h . At step 5 h , the decision is made whether to apply network connection affinity tuning. If the answer is “YES”, the sequence repeats at step 5 h . If the answer is “NO”, the sequence proceeds to step 5 i . Step 5 i requires a decision whether to configure SAP database for optimization. If the answer here is “YES”, then step 5 i is repeated. If the answer is “NO”, the sequence proceeds on to step 5 j . Step 5 j requires a decision whether to configure SAP database object. If the answer here is “YES”, then step 5 j is repeated. If the answer here is “NO”, then the sequence ends at step 5 k.
- Step 5 b of FIG. 5A SQL Server Memory Management
- memory management is a major consideration for the DBMS software, especially on a 32-bit system as memory can only be addressed up to 4 GB.
- This memory space limitation presents a good opportunity for tuning to help improve the overall system performance.
- the following memory management tuning techniques can improve the performance of DBMS running on a 32-bit system:
- AWE Address Windowing Extensions
- AWE lets applications acquire physical memory as non-paged memory, and then dynamically map views of the non-paged memory to the 32-bit address space. This enables memory-intensive applications such as Database Management System software to address more memory than it can be supported in the standard 32-bit address space.
- PAE switch In order for the OS to see beyond 4 GB of physical memory, PAE switch must be set in boot.ini system file. To set AWE, SQL Server must be run by an account with “Lock Page in Memory” permission. Also, there must be at least 3 GB of free memory available on the computer for SQL Server to run in AWE mode.
- Table II shows the SQL Server options.
- SQL Server dynamically allocates memory for optimal performance.
- the max and min server memory configuration settings exist as a way to override the default behavior of automatic memory allocation.
- Configuring memory as static is beneficial when other processes doing substantial work might make it difficult for SQL Server to dynamically allocate memory properly.
- To configure memory as static set min server memory and max server memory to the same value. This configuration effectively allocates a chunk of memory of the size indicated by the min and max server memory value.
- Configure SQL Server memory as static under the following conditions:
- the Set Working Set Size setting reserves an amount of physical memory for SQL Server that is equal to the server memory setting.
- the OS does not swap out SQL Server pages.
- the server memory is configured as static, set the Set Working Set Size value to one (1).
- the server memory is configured as dynamic, set the Set Working Set Size value to zero (0).
- Table III shows the relationship between max and min server memory and Set Working Set Size values.
- SQL Server is running on a standalone database server.
- SQL Server is the only application running on the database system.
- Table IV shows the settings for a standalone database server running SQL Server. For memory larger than 16 GB, do not set the /3 GB switch because Windows requires more than 1 GB to manage Address Windowing Extension (AWE).
- AWE Address Windowing Extension
- Table IV shows standalone database server settings for SQL Server 2000.
- SQL Server For other implementation such as two-tier client/server where database and application services are running on the same physical server, a user needs to manage memory for SQL Server differently. For example, if several applications are running on one server such as SQL Server and SAP R/3, allocate sufficient memory for both programs to run effectively. TABLE V illustrates the setting for SQL Server and an SAP R/3 instance. Following are some additional guidelines:
- Table V shows SQL Server 2000 and SAP R/3 settings.
- the affinity mask is a SQL Server option used to specify the CPUs on which SQL Server threads can run in a multiprocessor environment.
- the default value of zero (0) specifies that the OS scheduling algorithms determine the thread affinity.
- a nonzero value sets a bitmap that defines the CPUs on which SQL Server can run.
- Table VI shows sample binary values.
- SQL Server is the only application running on the system, set the affinity mask option to enable SQL Server to use all of the CPUs.
- set affinity mask option so that CPU time is allocated among all processes.
- the lightweight pooling parameter is used to configure SQL Server to use lightweight threads, or fibers.
- the use of fibers can reduce context switches by enabling SQL Server, rather than the OS scheduler, to handle scheduling.
- set the lightweight pooling parameter to one (1).
- the default value is zero (0), which specifies the threads mode.
- each user mode scheduler uses a single thread to control the scheduling of work requests on fibers.
- the number of fibers is controlled by the max worker threads parameter in SQL Server.
- Step 5 e of FIG. 5A Configure The Windows Threads, use the max worker threads parameter to specify the maximum number of Windows threads that SQL Server can use. Adjust this parameter to enable more threads for processing within SQL Server. Beware that if SQL Server uses too many threads, the OS becomes overloaded.
- Step 5 f of FIG. 5A Configure Scheduling Priority
- a value of one (1) for the priority boost parameter specifies that SQL Server run at a higher OS scheduling priority than it otherwise would.
- the default value of zero (0) disables priority boost option. Setting priority boost to one (1) can improve SQL Server performance, but can also keep other processes from getting sufficient CPU time. Set this value only if SQL Server is the only application running on the system.
- Parallel query allows SQL Server to perform a query in parallel by using multiple operating system threads.
- Parallel query is particularly useful when running complex queries with large amount of data as the jobs can be processed in parallel.
- Parallel query tuning technique can generate various effects for SAP R/3 systems.
- R/3 systems are Online Transaction Processing (OLTP) systems that execute large volumes of simple SQL statements.
- queries execute in parallel may not improve system performance because parallel query can consume multiple CPU resources and may prevent other queries from being processed and thereby slowing overall system performance. For this reason, the max degree of parallelism should be reduced to 50% of the number of available CPUs or to one (1), which disable parallelism.
- BW Business Warehouse
- APO Advanced Planner and Optimizer
- BW and APO systems benefit from parallelism, or setting the max degree of parallelism value to zero (0), which uses the number of available processors in the system, during the aggregate loading phases that are usually performed at night. This is particularly true when aggregate loading is done in a single process when no other users or batch jobs are using system resources.
- BW systems have the max degree of parallelism set to 1 for typical daily operations. Validate the degree of parallelism by performing the stress test and measuring performance improvement.
- a user's environment has a mixed mode R/3OLTP that is also used to synthesize BW or APO data
- One example is to set a job to use the zero (0) value at 1 A.M., during which the BW aggregates could synthesize for a few hours. Then schedule the value to be reset to one (1) before OLTP users log in and start using the system in the morning. Again, validate the degree of parallelism by performing the stress test and measuring performance improvement.
- Step 5 h of FIG. 5B Network Connection Affinity the network connection affinity is used in the following scenarios:
- connection affinity mask option can enhance performance in high-end, enterprise-level SQL Server environments that are running on computers with 16 or more CPUs.
- Connection affinity mask option defines a set of CPUs that will handle SQL Server network connections.
- a network reader thread is created for each port defined. This thread can be restricted to run on a defined set of CPUs with a specified mask.
- this option is useful when there are a significant number of network interactions (e.g. more than 10,000 per second) between the middle-tier application servers and the back-end SQL Server system.
- SQL Server Network Utility Use the Server Network Utility to define protocols and ports that SQL Server uses to monitor activity.
- a network reader thread is created for each port that is defined. This thread can be restricted to run on a defined set of CPUs with a specified mask. The network thread will distribute work items to schedulers running on the same set of CPUs as defined by the connection affinity mask.
- Scheduler within the context of SQL Server, is a function within SQL Server that controls the scheduling of threads and fibers in the system. These schedulers ensure SQL Server can maximize operating system resource usage in relation to key database actions.
- connection affinity mask in conjunction with the processor affinity mask system configuration option.
- the connection affinity mask is a subset of the affinity mask configuration option.
- connection affinity mask cannot be changed while SQL Server is running. To change the connection affinity mask, make the necessary change, shut down and restart the SQL Server instance.
- SAP Database Configuration there are some SQL Server settings that are specific to the SAP R/3 database. Unlike the server-wide parameter changes, which affect all of the databases on the server, the additional SQL Server settings that are specific to SAP R/3 database are set and controlled by the R/3 installation or upgrade process. To improve performance, disable the options Automatic Statistics Creation, Automatic Statistics Update, and ANSI nulls. When enabled, SQL Server automatically updates the statistics on table columns when a large number, or high percentage, of rows in the table change through update, insert, or delete operations. SQL Server automatically determines when to update statistics.
- each query will return a value of one (1).
- Step 5 j of FIG. 5B SAP Database Object Configuration, consideration must be placed on two database options autostats and page-level locks.
- the autostats and page-level locks options should be disabled for a few critical tables. This has proven over time to benefit performance of the R/3 application.
- Autostats is a statistical maintenance function. Autostats automatically update the statistics for a particular table when a “change threshold” has been reached. As a result, it can generate unwanted overhead on a system by initiating statistical updates during heavy workload processing and thereby adversely affecting the system performance. Verify the setting through Query Analyzer from within the context of the R/3 database and execute the following queries:
- SQL Server 2000 dynamic locking strategy automatically chooses the best locking granularity for queries in most cases. However, in some cases, it is best to disable the page-level locks and only allow index accessed at row or table level. Disable page-level locks to reduce overhead. Disable the page-level locks for the following tables: VBHDR, VBMOD, VBDATA, ARFCSDATA, ARFCRDATA, and TRFCQUEUE.
- DBMS Database Management System
- FIG. 6 is an illustration of final results which will be discussed later herein at the end of the drawings discussions.
- FIG. 7 demonstrates a 16-CPU partition of a 32-bit ES70000 system consisting of 4 subpods. Each subpod has 4 CPUs and a shared cache.
- partition 70 a is composed of a series of CPUs 0 , 1 , 2 , and 3 , designated as item 76 .
- the CPUs 4 , 5 , 6 and 7 are designated as item 77 .
- Each set of the CPUs 76 and 77 has its own shared cache unit.
- the two sets of CPUs 76 and 77 are connected to a crossbar 73 , which connects to a memory unit 72 .
- the partition 70 b is composed of a series of CPUs 8 , 9 , 10 and 11 , designated as item 78 , and CPUs 12 , 13 , 14 and 15 are designated as item 79 .
- Each of these sets of CPUs has a shared cache module.
- the CPUs 78 and 79 are connected to a crossbar 75 , which connects to a memory unit 74 .
- both memory units 72 and 74 can be accessed using the crossbar interconnects 73 and 74 .
- FIG. 8 demonstrates a 16-CPU partition of a 64-bit ES70000 system consisting of 4 processor/memory modules. Each processor/memory module has 4 CPUs with its own memory.
- the 16-CPU partition is a 64-bit ES7000 system, which consists of four processor/memory modules designated 80 a , 80 b , 80 c , and 80 d .
- a crossbar interconnect module 81 connects these processor/memory modules to each other.
- SAP processes in the same instance to run in the same process/memory module for a better utilization of local memory and reduce memory latency. For example, if there are 4 SAP instances running on this partition, set SAP processor affinity as follows:
- FIG. 9 shows the VIA network connection affinity for a 16-CPU server.
- the VIA network connection affinity for a 16-CPU server shown in FIG. 9 indicates four subpods 92 a , 92 b , 92 c , 92 d .
- Each subpod in the database server 30 has four CPUs. In the four subpods, the CPUs are numbered 0 through 15.
- Each subpod has a VIA connection indicated as VIA 0 , VIA 1 , VIA 2 and VIA 3 .
- each of the subpods 92 a . . . 92 d is connected to an application server, respectively marked as 90 a , 90 b , 90 c , and 90 d.
- connection affinity To achieve better performance, set network connection affinity to allow network connections to be handled evenly across all subpods. For example, if there is a 16-CPU server as in FIG. 9 , and SQL Server handles a large workload driven by four application servers, it is best to assign network threads that handle connections from each application server to run on a set of four CPUs as shown in FIG. 9 .
- the connection affinity can be explained as follows:
- FIG. 6 illustrates the proof point resulting from applying the process.
- FIG. 6 there is seen an illustrative graph, which shows the number of processors involved on the X axis, and the number of users involved on the Y axis.
- Described herein has been a series of software optimizing processes for a three-tier client/server SAP Sales and Distribution implementation. Tuning techniques are applied to the software layer of the Operating System, the SAP application, and the Database Management System software to provide the most efficient operation in processing customer Sales and Distribution (SD) transactions running on a multiprocessor server.
- SD Sales and Distribution
Abstract
Description
- 1. CROSSBAR INTERCONNECT (CI): A scalable switch device consists of multiple, independent data paths, or pipes that connect processors and Peripheral Component Interconnect (PCI) modules to memory.
- 2. PROCESSOR MODULE (POD): A module that consists of a crossbar interconnect (CI) and one or two processor submodules (subpod).
- 3. PROCESSOR/MEMORY NODULE: A hardware module consisting of processor and memory components for 64-bit ES7000 servers. Each module provides mounting locations and supports an interconnection circuitry for four processor chips and 16 dual inline memory modules (DIMMs).
- 4. PROCESSOR SUBMODULE (SUBPOD): It is one of the two processing units in a processor module (pod). One processor submodule contains up to four processors, first- and second-level cache, shared cache, and interconnection logic.
- 5. ES7000: A family of Unisys multiprocessor servers. ES7000 is a multiplatform server supporting Windows™, Linux, MCP operating systems, OS2200 systems and other applications.
- 6. SHARED CACHE: A cache shared by multiple processors in the same processor submodule.
- 7. VIRTUAL INTERFACE ARCHITECTURE (VIA): Virtual Interface Architecture (VIA) is a communication protocol that provides a direct path for applications, bypassing the operating system interfaces and achieving very high throughput. Giganet cLAN is the first native implementation of VIA and is used in the Unisys benchmark environment. Giganet cLAN delivers high throughput and low latency interconnection of multiple servers. Giganet cLAN provides full-duplex throughput of 1.25 Gb/s (20 Gb/s aggregate). Due to small port-to-port latency and minimal CPU overhead, Giganet cLAN is used for data transferring between application servers and the database server.
- 8. DIRECT I/O BRIDGE (DIB): DIB is hardware unit in the ES7000 where the peripheral component interconnect (PCI) buses are located. It provides a path from the processors and memory to the PCI buses.
- 9. 32-BIT ARCHITECTURE: 32-bit is a term applied to processors, and computer architectures that manipulate the address and data in 32-bit “chunks” of 4 bytes data.
- 10. 64-BIT ARCHITECTURE: A computer architecture described as “64-bit” generally has integer registers that are 64 bits wide and thus directly supports 64-bit “chunks” of data.
- 11. INTERRUPTS: Interrupts are signals that a device can send to a processor when the device is ready to accept or send information.
- 12. DATA LOCALIZATION: Data localization refers to a method of placing data in a local cache or the nearest memory area in order to provide fast access to the data and reduce memory latency.
- 13. SYSTEM LATENCY: System latency refers to the delay required to complete a given operation. For example, memory latency describes the delay introduced when a data needs to be transferred from memory to the processors.
- 14. CACHE COHERENCY: The synchronization of data located in one or more caches and the memory so that data retrieval from any location will return the most recently written data.
- 15. THREADS: Threads are the smallest units of execution that runs a program or performs a task.
- 16. FIBERS: Fibers are lightweight SQL Server threads. Using fiber can reduce the number of context switches by enabling SQL Server, rather than the OS scheduler, to handle scheduling.
- 17. CONTEXT SWITCH: Context switch is a state where the OS in multiprocessing environment suspends one process from execution on a CPU and starts processing another process. The OS needs to record the environment or context of the suspended process so that it can resume the service for the suspended process in the future. Context switch is expensive. To achieve good performance, it is necessary to reduce the context switch management overhead or to have an effective scheduler that does not require too many context switches.
- 18. USER-NODE SCHEDULER (UMS): UMS is SQL Server scheduler. When SQL Server is started, a UMS scheduler is created for each processor in the system. These UMS schedulers control the scheduling of threads and fibers in the system. These schedulers ensure SQL Server can maximize operating system resource usage in relation to key database actions.
- 19. DATABASE: A database is information set with a regular structure. Any set of information may be called a database. Nevertheless, the term was invented to refer to computerized data, and is used almost exclusively in computing.
- 20. MAX WORKER THREADS: Use the max worker threads parameter to specify the maximum number of Windows threads that SQL Server can use. One can adjust this parameter to enable more threads for processing within SQL Server. If SQL Server uses too many threads, the OS becomes overloaded.
- 21. MAX SERVER MEMORY: SQL Server allocates memory dynamically. Set the max server memory option to specify the maximum amount of memory, in megabytes (MB), that SQL Server will allocate to the buffer pool. Because SQL Server will take some time to release memory, set the max server memory option so that SQL Server leaves some memory free for other applications. The default value is 2147483647, which directs SQL Server to acquire as much memory as it can from the system while dynamically allocating memory as other applications require it. This is the recommended setting for a dedicated SQL Server system.
- Use the max server memory option in conjunction with min server memory option to designate the upper and lower limits for memory allocated by SQL Server. The max server memory option takes effect immediately, with no need to restart SQL Server.
- 22. MIN SERVER MEMORY: Use the min server memory option to specify the minimum amount of memory, in megabytes (MB) that is to be allocated to the SQL Server buffer pool. Setting this parameter is useful in systems in which SQL Server might reserve too much memory for other applications. For example, if the server is used for print and file services as well as for database services, SQL Server might relinquish too much memory to these applications and slow down user response times.
- The default value of min server memory is zero (0), which enables SQL Server to dynamically allocate and de-allocate memory. It is the recommended setting, but change the value if the server is not dedicated to SQL Server. This option takes effect immediately, with no need to restart SQL Server.
- 23. SET WORKING SET SIZE: The set working set size option specifies that the memory allocated by SQL Server cannot be swapped out, even if that memory can be more effectively used by another process. This option reserves physical memory space for Microsoft® SQL Server™ that is equal to the server memory setting. Do not set this option if SQL Server is allowed to use memory dynamically. Use this option only when min server memory and max server memory are set to the same value. In this case, SQL Server allocates a static amount of non-pageable memory.
- 24. APPLICATION: Application software designed to perform specific functions. SAP is an example of a business application allowing users to perform business transactions.
- 25. APPLICATION LEVEL: Application level includes all components in the application tier. These components provide application services, such as SAP R/3.
- 26. APPLICATION SERVER: An application server refers to a computer system that provides application services, e.g. the SAP R/3 business application used in the benchmark environment. This business application allows users to process specific business requests.
- 27. BENCHMARK DRIVER: A benchmark driver refers to a toolkit that simulates user workload on the presentation tier of the three-tier SAP benchmark environment.
- 28. BENCHMARK EXECUTION: Benchmark execution is the process of running the benchmark to simulate user workload and to measure the performance of the SAP system.
- 29. BENCHMARK RAMP-UP PHASE: This is the initial phase in the SAP SD benchmark. It comprises one or more users logging on the SAP system.
- 30. BENCHMARK TEST: A benchmark test measures the performance of different computer systems. The benchmark results offer objective statements about how a system performs.
- 31. BENCHMARK USER: A benchmark program generates benchmark users in order to simulate real-world users performing SAP transactions.
- 32. BUS: A common internal interface in a computer that provides a path for transferring data, address, control, or status signals from one part of the computer to others.
- 33. CACHE: A high-speed memory or storage device that helps reduce the time required to read and write data to a slower device, such as main memory or hard drive. When cache memory is installed, the processor looks for data in the cache first. If the data is found in cache because it has been read previously, the processor does not have to read the data from main memory.
- 34. CALL CENTER AGENT: A SAP user who is using a SAP call center application module. The call center user is considered an experienced user who needs to interface with the SAP GUI frequently.
- 35. CHIP: A group of circuits designed to perform related tasks.
- 36. CLUSTER: A cluster is a group of four-processor building blocks.
- 37. CONCURRENT USERS: Refers to the users who connect to an SAP R/3 system to perform one or more activities within a given interval of time.
- 38. CENTRAL PROCESSING UNIT (CPU) TIRE: CPU time is an indicator of processor activity observed during a specific interval. CPU time is often measured in the unit of % Processor time, which is the percentage of elapsed time that the processor spends to execute a non-idle thread.
- 39. DATA FILE: Files that contain information that is essential for running SQL Server application.
- 40. DATABASE LEVEL: Database level includes all components in the database tier. These components are responsible for storing, retrieving and providing data to the application tier.
- 41. DATABASE SERVER: A database server is a computer that provides database services enabled by Database Management System software. The database services allow users to store, retrieve, and manipulate data. The database services listen to and process user requests by communicating with application servers. The Database Management System software for the benchmark is 32-bit Microsoft SQL Server 2000.
- 42. DELIVERY: A document contains delivery information of the order from a customer.
- 43. DIALOG RESPONSE TIME: Dialog response time is a measuring unit determining how fast the system responds to a user request. In the benchmark implementation, an absolute limit of the dialog response time is two seconds.
- 44. DIALOG STEP: Dialog step is a single unit of operation performed by a dialog work process.
- 45. DIALOG USERS: This term refers to the users who are currently performing the steps in the Sales and Distribution (SD) transactions. There are a total of 18 dialog steps in the SD benchmark.
- 46. DISK STRIPING: Also known as
RAID 0 where data is written in sequential sectors across multiple drives. Disk striping offers no protection for data because there is no data redundancy, but can increase performance dramatically as information can be written to or retrieved from several drives at once, minimizing the overall seek time in large files. - 47. ENTERPRISE RESOURCE PLANNING (ERP): An information system or process integrating all manufacturing and related applications for an entire enterprise. ERP systems permit organizations to manage resources across the enterprise and completely integrate manufacturing systems.
- 48. FIRST LEVEL CACHE: The onboard memory built into the same chip with a microprocessor. The processor first checks the first-level cache to see if it holds data previously retrieved from the main memory.
- 49. GIGABIT ETHERNET: Gigabit Ethernet is a networking protocol built on top of the Ethernet protocol. Gigabit Ethernet yields a data transfer rate of 1,000 megabits per second (Mbps), or 1 gigabit per second (Gbps). Gigabit is a dominant protocol in high speed local area network backbones and server connectivity. In the benchmark environment, Gigabit network is used for transferring data between application servers and presentation servers.
- 50. HARDWARE: Hardware refers to physical components of a computer system that allow a computer to operate. Main components include CPU, memory, peripheral devices, etc.
- 51. HOST BUS ADAPTER (HBA): HBA is a hardware device that typically provides an interface from peripheral devices to the processor.
- 52. HYPER-THREADING: An Intel™ technology that allows a single physical processor to execute multiple threads or instruction streams simultaneously, potentially providing greater throughput and improved performance. These processors contain two architectural states on a single processor core, making each physical processor act as two logical processors for the operating system. However, the two logical processors still share the same execution resources of the processor core, so performance gains do not approximate two complete, physical processors.
- 53. IDENTIFYING A COMPONENT/SUBCOMPONENT: A process of evaluating each tier and categorizing each component in an appropriate group for improvement opportunities. The components can be classified as hardware and software. Within each component, one can further break down the subcomponents. For example, within the software component, there are subcomponents, which include operating system, SAP application, and Database Management System software.
- 54. INVOICE: An invoice document that is associated to a particular order.
- 55. I/O BRIDGE: Input/Output Bridge connects Peripheral Component Interconnect (PCI) bus to processors and memory. The I/O Bridge connects to the processor and memory by the Crossbar Interconnect (CI).
- 56. INTERLEAVING: A method of addressing memory to spread the memory service requests across the memory modules and reduce the time waiting for service.
- 57. KERNEL TIME: Kernel time indicates the processor activity for executing system code. Kernel time is often referred as privileged time and measured as a percentage of elapsed time that the process threads are spent executing system code in privileged mode.
- 58. LIST ORDER: A business transaction that allows a user to list all of the orders created earlier.
- 59. LOCKING SITUATION: Locking situation is a state where an object is being used exclusively by one process. During that period, the object is being blocked and cannot be accessed by another process. Too many locking situations may hinder system performance as many processes must spend time waiting for objects to become available.
- 60. LOGICAL CPUs: See definition of “Hyper-Threading”.
- 61. LOGICAL UNIT NUMBER (LUN): An identifier assigned to a storage volume. Each storage volume is assigned a unique logical unit number.
- 62. NETWORK: Network is a group of computers and associated peripherals connected by a communication channel capable of sharing files and other resources between several users.
- 63. ONLINE USERS: This term refers to a person who is connecting to a computer system to perform some Sales & Distribution (SD) transactions via the SAP Graphical User Interface (GUI).
- 64. OPERATING SYSTEM: Operating System is the software responsible for allocating hardware resources and interfacing with users.
- 65. OPTIMAL PERFORMANCE: Optimal performance refers to the point at which a server is capable of handling the maximum number of users without the performance degrading beyond a predetermine response time limitation. In SAP SD benchmark implementation, the response time must be less than 2 seconds.
- 66. OPTIMAL RESULT: Optimal result is the point at which a server is capable of handling the maximum workload without performance degradation and yields a response time within the predetermined limit. In SAP SD benchmark implementation, the response time must be less than 2 seconds.
- 67. ORDER: A document called a customer order created by a SAP user whose role is a sales representative.
- 68. PERFORMANCE PARAMETERS OF AN SAP SYSTEM: Performance parameters are means to measure the performance of an SAP system. The most common parameters include dialog response time, database request time, CPU utilization, memory consumption, I/O utilization, and network utilization.
- 69. POWER USERS: Refers to the users who are controlling the Sales and Distribution (SD) process.
- 70. PRESENTATION LEVEL: Presentation level includes all components in the presentation tier that provide interfaces between users and the application, as well as the database tiers.
- 71. PRESENTATION SERVER: Also refer to as driver. A presentation server is a computer responsible for formatting the Graphical User Interface. It is the interface between the users and computers providing required services. In general, a user enters a request via a presentation server. The request will be forwarded to an application and a database server. Once the presentation server retrieves the result back, it formats and presents the result to the user.
- 72. PERIPHERAL COMPONENT INTERCONNECT (PCI) BUS: PCI bus is a local bus standard with multiple PCI slots that support PCI cards. The PCI bus is the interface between the I/O Bridge and the PCI card.
- 73. PERIPHERAL COMPONENT INTERCONNECT (PCI): A standard that enables communication between processors and peripheral devices.
- 74. POPULAR TRANSACTIONS: Refer to frequently accessed business transactions by SAP users. In the SAP SD benchmark implementation, the most popular transactions include create an order, create a delivery, display a customer order, change the delivery, list the order, and create an invoice.
- 75. PROTOCOL: A set of rules or standards describing methods to achieve compatible transmission and receipt of data (e.g. message packets) over a network.
- 76. REDUNDANT ARRAYS OF INEXPENSIVE DISKS (RAID): Multiple disk units combined into single logical device to increase data availability and performance.
- 77. SALES AND DISTRIBUTION (SD): SD is an application module of the SAP software, which deals with the aspect of sales and distribution, e.g. creating customer order, delivery and invoice.
- 78. SYSTEMS AND APPLICATION PRODUCTS (SAP): SAP is the company that supplies the SAP R/3 software, which is used for financial, Human Resources (HR) and plant maintenance transactions and reporting.
- 79. SAP BENCHMARK TOOLKIT: SAP benchmark toolkit is a toolset provided by SAP. The toolkit consists of programs and script files that allow a user to simulate SAP user workload.
- 80. SAP DATA FORMAT: SAP data format is a data layout required by SAP. Before a user request can be processed or displayed on the SAP GUI program, the data must be converted into the SAP data format.
- 81. SAP R/3 STANDARD APPLICATION BENCHMARK: The SAP R/3 standard application benchmark is a standardized industry benchmark provided by SAP. It measures hardware and database performance using the SAP application. It consists of script files that simulate typical transactions and the workflow of an SAP R/3 user. A predefined SAP client database contains sample company data used in the testing procedure.
- 82. SCRIPT FILES: Script files consist of a series of executable programs or commands. Script files are used as part of the benchmark tools in order to simulate SAP user workload in the benchmark environment.
- 83. SECOND-LEVEL CACHE: Cache memory built into separate memory chips. Second-level cache is memory that a processor can access more quickly than main memory (regular RAM).
- 84. STACKING: A method of addressing memory where consecutive memory service requests access the same memory module.
- 85. STORAGE PROCESSOR (SP): An intelligent RAID controller that is enclosed within a storage device.
- 86. STORAGE SYSTEM: A physical component that allows users to store data.
- 87. TRANSMISSION CONTROL PROTOCOL/INTERNET PROTOCOL (TCP/IP): A suite of communication protocols used for transmitting data over networks. In addition, TCP/IP is widely used to connect hosts on the Internet. All servers in the benchmark environment are connected over TCP/IP network.
- 88. THREE-TIER CLIENT/SERVER ARCHITECTURE: The three-tier client/server architecture consists of three service layers including a database, an application, and a presentation layer. Those services are running on different servers. The three-tier client/server configuration provides for the database layer and application layer to exist on separate systems with the workload driven by a presentation server.
- 89. TIER: Refers to a dedicated layer of components working together to provide specific services. The three-tier client/server architecture consists of the database, the application, and the presentation tiers. Tier and layer may be used interchangeably.
- 90. TRANSACTION LOG FILE: The transaction log is used to record changes to the database, thus allowing the system to recover in the event of a failure.
- 91. TUNING TECHNIQUE: A methodology of changing the parameters of a device or a system to achieve a specified or improved performance.
- 92. TYPICAL TRANSACTIONS: Refers to business transactions used by SAP users. The typical transactions are necessary for users to perform their jobs but are not executed as often as the “popular” transactions.
- 93. USER INTERFACE PROGRAM: A user interface program allows a user to interact with a computer. The user interface program allows a user to enter a request and presents a result to the user in an appropriate format. A special form of a user interface program is called Graphical User Interface (GUI). GUI takes advantage of the computer's graphical capability to make the program easier to use. User interface programs including GUI run on a computer called a presentation server.
- 94. USER THINK TIME: User think time refers to the time a user needs to process the information before entering additional inputs or moving onto the next screen. For benchmark implementation, the user think time is 10 seconds.
- 95. INDEXPROPERTY FUNCTION: A function in SQL Server that returns the named index property value given a table identification number, index name, and property name.
- 96. <SAPSIDDB> PARAMETER: A unique identifier for a SAP database.
- 97. PROFILE PARAMETERS: SAP R/3 configuration parameters that allow a user to control certain aspects of SAP behavior like buffer size, memory size, database specific performance options and work process affinity.
- 98. SAP INSTANCE: An SAP instance is an administrative unit that combines SAP components that provide one or more services and can be started and stopped together. The instance usually contains more than one SAP work processes. Each SAP work process requires a certain amount of memory to store data temporarily during run time.
- 99. TRANSACTION SNRO: SNRO is number range object maintenance transaction in SAP, which allows users to maintain number range objects. Some SAP business documents require a unique identifier key. The key is created using numerical or alphanumerical characters stored in number ranges. The transaction SNRO allows users to maintain number ranges such as define the ranges, buffer the number ranges, etc.
- 100. SQL SERVER: This is a Microsoft database management server.
- 101. BACKEND SQL SERVER SYSTEM: Backend SQL Server system is referring to a computer system providing database services where user has no direct contact. To minimize confusion, simply refer as SQL Server system.
- 102. SQL SERVER INSTANCE: One SQL Server instance refers to one copy of SQL Server software running on a computer system.
- 103. SQL SERVER 2000: The current version of Microsoft database management software often referred to as SQL Server.
- 104. SQL SERVER 2000 SERVICE PACK: A Service Pack (more commonly, SP) is the mean by which Microsoft distributes updates, bugs correction and new features for SQL Server 2000.
- 105. SQL AS AN APPLICATION: SQL should be referred to as SQL Server, more specifically SQL Server 2000. SQL Server 2000 is a Database Management System (DBMS) software or application. Software, software program, program and application are the same and can be used interchangeably.
- 106. SQL STATEMENTS: Method for querying or manipulating the SQL Server database. For example: CREATE TABLE, DROP TABLE, ALTER TABLE, RENAME TABLE.
- 107. AUTOSTATS: A statistical maintenance function in SQL Server. Autostats automatically update the statistics for a particular table when a “change threshold” has been reached.
- 108. PAGE-LEVEL LOCK: The locking granularity for queries in SQL Server. For performance reason, it is better to use less intrusive row-level or table-level lock as opposed to page-level lock.
- 109. PAGING FILES: Paging files are system files located on disks. Paging files are used for storing temporary data required during data processing when the system does not have enough physical memory to store the data.
- 110. TABLE BUFFERING: Table buffering is a mechanism to buffer or store some tables on an application server in order to minimize the amount of data being sent to and from the database server.
-
- a. OPERATING SYSTEM (OS) (
Step 2 b): The OS manages the hardware and software resources of the system. On a server, these resources include such things as the processor, memory, disk space, etc. It also provides a stable, consistent way for applications to deal with the hardware without having to know all the details about the hardware. - b. SAP APPLICATION (
Step 2 c): SAP application is a suite of business software applications developed by SAP and runs on the OS. SAP application requires Database Management System software to manage and store data. - c. DATABASE MANAGEMENT SYSTEM SOFTWARE (DBMS) (
Step 2 d): The DBMS is a suite of computer programs designed to manage a database, a large set of structured data, and to run operations on the data requested by numerous users.
- a. OPERATING SYSTEM (OS) (
TABLE I | ||||
Maximum No. | ||||
64-Bit | Maximum | Of | ||
Windows | Technology | Memory | Processors | |
Server 2003 | Support | Support | | |
Standard | No | |||
4 |
4 | |||
Edition | ||||
Enterprise | Yes | 32 GB (32-bit), | 8 | |
Edition | 64 GB (64-bit) | |||
Datacenter | Yes | 64 GB (32-bit), | 32 (32-bit), | |
Edition | 512 GB (64-bit) | 64 (64-bit) | ||
| No | 2 |
2 | |
- 1. SAP Memory Management (
Step 4 b): Each SAP process requires a certain amount of memory to run. By allocating the proper amount of memory to a SAP process so that it can run effectively without starving other processes that are running on the same system can improve overall system performance. - 2. Configure The SAP Work Process Type And Amount (
Step 4 c): The SAP application processes, also referred to as work processes, perform unique functions, such as update, dispatch etc. . . . . To achieve optimal results, configure the correct types of work process as well as the number of work processes based on hardware resources and workload. - 3. SAP Processor Affinity (
Step 4 d): The ability to assign SAP work processes to run on specific processors is called SAP processor affinity. SAP processor affinity improves overall system performance because processes share the data, which resides on the shared cache among groups of processors and thereby minimizes system latency. - 4. Table Buffering (
Step 4 e): SAP uses various buffers such as table buffers, program buffers, repository buffers, etc. . . . and these buffers are located on an application server. One way to improve performance is to buffer some tables on an application server to minimize the amount of data being sent to and from the database server. Table buffering offloads processing to the application servers, reducing the stress on the database server. - 5. Number Range Buffering (
Step 4 f): When a SAP business document such as a customer order, a billing document, a shipping document etc. . . . is generated, a document number is assigned. The document numbers are kept as number ranges in a database table called NRIV. When many users are working at the same time, system bottlenecks can occur in number range assignment because the NRIV table remains locked until a process that issues a lock request completes the number assignment. One way to improve system performance is to buffer the number range objects. Selecting the appropriate value for the objects helps to avoid most direct access to the table NRIV. When configuring SAP R/3 instances, care is taken to avoid buffer swaps during the benchmark run. The sizes of all buffers, like the ABAP program buffers, are set accordingly. In the SD benchmark, the buffering of number ranges for certain SAP R/3 objects is permitted. Each SAP R/3 instance reserves its own ranges at startup and maintains them locally, thus saving the accesses to the NRIV table of the database that would otherwise provide unique identifiers.
There are also cases in which the use of a local update dramatically reduces scalability. Contention on table NRIV may result when documents are created with automatic numbering using un-buffered number range objects. In case of a local update, there is no database commit until the updates are completely processed, which can lead to severe serialization effects on the database table NRIV.
If the number range object is buffered in main memory, no database access is necessary, and no contention will result. If it is not, an update on the database table NRIV has to take place.
2. Make Sure Physical Memory Is Available: If there is not enough physical memory required for an SAP instance to run, consider reducing the number of instances or SAP work processes. Alternatively, consider increasing virtual memory by adding paging files. However, swapping to disk I/O is a lot slower than memory. Thus, adding too many or large paging files without having enough physical memory can have adverse performance impacts.
3. Understand The Limitation Of The Hardware Architecture: If a user uses 32-bit technology, the addressable memory space is limited to 4 GB. If the system has physical memory larger than 4 GB and has SAP instance(s) that require more than 4 GB of memory, then enable the use of /PAE.
4. Allocate Enough Memory For SAP And Other Applications (if any) In The Same Server: If SAP and other applications, such as file and print server services, are running on the same server, make sure sufficient memory is allocated to both applications so that they have enough memory to run effectively.
2. Main Memory Buffering: The number range is buffered in main memory. There is no lock wait problem. It is a fast and efficient way because accessing the data from the memory on an application server is faster than from the database server. On the other hand, there are some limitations. There may be some gaps in the number allocation and the numbers may be assigned in a non-consecutive sequence.
3. Local, On Instance Level Buffering: The number range is temporarily stored on the database table, called NRIV_LOKAL. The number range and SAP instance number are used as part of a key. The performance is improved because the lock/wait problem is reduced. The advantage is that the number allocation is almost gap-free. However, the number may be assigned in a non-consecutive sequence. The drawback is that locks still occur within an instance. If high throughput is required, it is necessary to have users simultaneously work on many SAP instances.
4. Local, On Instance And Work Process Level: The number range is temporarily stored on the database table, called NRIV_LOKAL. The number range, SAP instance number, and work process number are used as part of a key. The lock/wait problem is eliminated. The number range allocation is almost gap-free. However, the number may be assigned in a non-consecutive sequence.
-
- 1. SQL Server Memory Management (
Step 5 b): Memory management is the ability of SQL Server to allocate, free, and generally manage memory resources. Memory management is critical to the performance of a 32-bit system due to the addressable memory space limitation. On a 32-bit system, memory can only be addressed up to 4 GB. It is not a critical issue on a 64-bit system as memory can be addressed up to 4*232 GB. - 2. SQL Server Processor Affinity (
Step 5 c): The affinity mask option is used to specify the CPUs on which SQL Server threads can run in a multiprocessor environment. The default value of zero (0) specifies that the OS scheduling algorithms determine the thread affinity. A nonzero value sets a bitmap that defines the CPUs on which SQL Server can run. - 3. Lightweight Threads Or Fibers (
Step 5 d): The lightweight pooling is an option to configure the SQL Server to use lightweight threads, or fibers. Using fibers can reduce the number of context switches by enabling SQL Server, rather than the OS scheduler, to handle scheduling. If SQL Server is running on a multiprocessor system and a large number of context switches occur, try setting the lightweight pooling option to one (1). The default value, zero (0), specifies the threads mode. Use the lightweight pooling option to provide a mean of reducing the system overhead associated with the excessive context switching sometimes seen in symmetric multiprocessor (SMP) environments. When excessive context switching is present, lightweight pooling may provide better throughput by performing the context switching inline, thus helping to reduce user/kernel ring transitions.
- 1. SQL Server Memory Management (
-
- 4. Configure The Windows Threads (
Step 5 e): Use the max worker threads parameter to specify the maximum number of Windows threads that SQL Server can use. Adjust this parameter to enable more threads for processing within SQL Server. If SQL Server uses too many threads, the OS may become overloaded. - 5. Configure The Scheduling Priority (
Step 5 f): A value one (1) for the priority boost parameter specifies that the SQL Server run at a higher OS scheduling priority than it normally would. The default value of zero (0) disables priority boost option. Setting the priority boost to one (1) can improve SQL Server performance, but it can keep other processes from getting sufficient CPU time. Set this value to one (1) if SQL Server is the only program running on the computer system. - 6. Parallel Query (
Step 5 g): The option to execute queries in parallel in the SAP R/3 system can impact the overall performance of the system. In some cases, this option greatly improves the SAP R/3 performance. - 7. Network Connection Affinity (
Step 5 h): In some cases, network connection affinity greatly improves the performance of the SAP R/3 system. In an OLTP environment, the connection affinity mask option can enhance performance in high-end, enterprise-level SQL Server environments that are running on computers with 16 or more CPUs. In particular, this option is useful when there are a significant number of network interactions (more than 10,000 per second) between the middle-tier application servers and the back-end SQL Server system. - 8. SAP Database Configuration (
Step 5 i): There are some SQL Server settings that are specific to the SAP R/3 database. Unlike the server-wide parameter changes, which affect all of the databases on the server, the additional SQL Server settings that are specific to SAP R/3 database are set and controlled by the R/3 installation or upgrade process. To improve performance, disable the options Automatic Statistics Creation, Automatic Statistics Update, and ANSI nulls. - 9. SAP Database Object Configuration (
Step 5 j): Within the database, there are two options: (i) autostats; and (ii) page-level locks that should be disabled for a few critical tables. This has proven over time to benefit performance of the R/3 application.
- 4. Configure The Windows Threads (
-
- The SQL Server instance no longer dynamically manages the size of the address space.
- All memory is acquired at startup and remains available until shut down.
- Memory pages using AWE come from non-paged pool. In other words the memory pages of the instance will not be swapped out.
-
- Address Windowing Extension enabled
2. Static vs. Dynamic Memory: Memory configuration for SQL Server depends on the following factors: - The existence of SQL Server and other applications in the same system;
- The amount of available memory
Based on these two factors, assign the appropriate values to the SQL Server options.
- Address Windowing Extension enabled
TABLE II | |||
SQL Server Options | Abbreviation | ||
min server memory (MB) | MIN (MB) | ||
max server memory (MB) | MAX (MB) | ||
set working set size | SWS | ||
awe enabled | AWE | ||
-
- Running SQL Server and other applications on the same system
- AWE option is enabled
TABLE III | ||||
Set working set size | ||||
Server memory | Memory | value | ||
Max = min | Static | 1 | ||
Max < > min | Dynamic | 0 | ||
TABLE IV | ||||||
AWE | ||||||
0- | ||||||
Total | disable | |||||
RAM | 1- | /3 | ||||
(GB) | MAX (MB) | MIN (MB) | SWS | enable | GB | /PAE |
<=2 | 2147483647 | 0 | 0 | 0 | N | N |
>2 <= 4 | 2147483647 | 0 | 0 | 0 | Y | N |
>4 <= 8 | RAM − 1000 MB | RAM − | 0 | 1 | Y | Y |
1000 MB | ||||||
>8 <= 16 | RAM − 1000 MB | RAM − | 0 | 1 | Y | Y |
1000 MB | ||||||
>16 | RAM − 2000 MB | RAM − | 0 | 1 | N | Y |
2000 MB | ||||||
-
- Allocate memory for SAP R/3 by using the PHYS_MEMSIZE parameter in the SAP R/3 profile. An SAP R/3 profile is a configuration file that allows user to control certain aspects of SAP behavior like buffer size, memory size, database specific performance settings and work process affinity.
- Add 1 GB of additional memory to the max server memory option for AWE management for server with memory larger than 16 GB.
- Set the min server memory value to a value less than 16 GB because SAP R/3 requires 3 GB of physical memory.
TABLE V | |||||||||
MAX | MIN | AWE | |||||||
R/3 | (MB) | (MB) | 0- | ||||||
Total | Memory | as % | as % | disable | |||||
SAP R/3 | RAM | as % of | of | of | 1- | ||||
Instance | (GB) | RAM | RAM | RAM | SWS | enable | /3 GB | /PAE | |
Central | <=3 | <45% | 45% | 45% | 1 | 0 | N | N | |
(Cl) | |||||||||
Update | <=3 | <40% | 50% | 50% | 1 | 0 | N | N | |
(UP) | |||||||||
Cl or UP | >3 <= 4 | 1 GB | 90% − | 90% − | 1 | 0 | | N | |
1 |
1 GB | ||||||||
Cl or UP | >4 <= 8 | X GB | 90% − X | 90% − |
0 | 1 | Y | Y | |
GB | GB | ||||||||
Cl or UP | >8 <= 16 | X GB | 90% − X | 90% − |
0 | 1 | Y | Y | |
GB | GB | ||||||||
Cl or UP | >16 | X GB | 90% − | 90% − | 0 | 1 | N | Y | |
(X + 1) | (X + 1) | ||||||||
GB | GB | ||||||||
TABLE VI | ||||
Decimal values | Binary values | Hex values | ||
15 | 1111 | 0xf | ||
255 | 11111111 | 0xff | ||
65535 | 1111111111111111 | 0xffff | ||
-
- SQL Server needs to handle a large number of network requests from clients over the VIA transport.
- Provide workload balancing and data locality.
The connection affinity mask is an option provided by SQL Server 2000 Service Pack (SP) 1 or later, which provides performance enhancement through the use of VIA transport protocol where a network reader thread is created for each port defined. This thread can be restricted to run on a defined set of CPUs with a specified mask. The network thread will only distribute work items to schedulers running on the same set of CPUs as defined by the connection affinity mask. The work items from the connections behind a VIA port are handled by a restricted number of CPUs as defined by the connection affinity mask. This feature provides the ability to partition the workload.
-
- The VIA port number is not the same as the TCP port number.
- The connection affinity mask is represented in hexadecimal, preceded by 0x or 0X.
- The mask is a bitmap in which the rightmost bit specifies the lowest-order CPU (0); the next rightmost bit specifies the next lowest-order CPU (1), and so on.
- A one-byte connection affinity mask covers up to eight CPUs in a multiprocessor computer, a two-byte mask covers up to 16 CPUs, a three-byte mask covers up to 24 CPUs, and a four-byte mask covers up to 32 CPUs.
- To enable connection affinity on a specific CPU, set the bit corresponding to this CPU in the connection affinity mask to one (1).
- When all bits are set to zero (0), or when a connection affinity mask is not specified, SQL Server network I/O processing is performed by any of the CPUs that are eligible to process SQL Server threads.
Value | Description | Value returned |
IsAnslNullDefault | Database follows SQL-92 | 1 = TRUE |
rules for allowing null | 0 = FALSE | |
values. | NULL = Invalid | |
input | ||
IsAutoCreateStatistics | Existing statistics are | 1 = TRUE |
automatically updated | 0 = FALSE | |
when the statistics | NULL = Invalid | |
become out-of-date | input | |
because the data in the | ||
tables has changed. | ||
IsAutoUpdateStatistics | |
1 = TRUE |
database option is | 0 = FALSE | |
enabled. | NULL = Invalid | |
Input | ||
-
- SELECT INDEXPROPERTY (OBJECT_ID (‘VBHDR’), ‘VBHHDR˜0’, ‘IsPageLockDisallowed’)
- SELECT INDEXPROPERTY (OBJECT_ID (‘VBDATA’), ‘VBDATA˜0’, ‘IsPageLockDisallowed’)
- SELECT INDEXPROPERTY (OBJECT_ID (‘VBMOD’), ‘VBMOD˜0’, ‘IsPageLockDisallowed’)
- SELECT INDEXPROPERTY (OBJECT_ID (‘ARFCSDATA’), ‘ARFCSDATA˜0’, ‘IsPageLockDisallowed’)
- SELECT INDEXPROPERTY (OBJECT_ID (‘ARFCRDATA’), ‘ARFCRDATA˜0’, ‘IsPageLockDisallowed’)
-
- All work processes for the first instance run on
CPUs - All work processes for the second instance run on
CPUs - All work processes for the third instance run on
CPUs - All work processes for the fourth instance run on
CPUs
- All work processes for the first instance run on
-
- All work processes for the first instance run on
CPUs - All work processes for the second instance run on
CPUs - All work processes for the third instance run on
CPUs - All work processes for the fourth instance run on
CPUs
- All work processes for the first instance run on
-
-
Application Server 1 connects to the database server throughVIA port 1400 and the network threads are running onCPUs -
Application Server 2 connects to the database server throughVIA port 1401 and the network threads are running onCPUs -
Application Server 3 connects to the database server throughVIA port 1402 and the network threads are running onCPUs -
Application Server 4 connects to the database server throughVIA port 1403 and the network threads are running onCPUs
-
-
- 10,400 users on a 16-processor ES7000 system with response time of 1.83 seconds and 99 percent processor utilization.
- 14,400 users on a 24-processor ES7000 system with response time of 1.83 seconds and 89 percent processor utilization.
- 26,000 users on a 32-processor ES7000 system with response time of 1.97 seconds and 93 percent processor utilization.
Claims (21)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/157,395 US7805706B1 (en) | 2005-06-21 | 2005-06-21 | Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers |
US12/862,229 US20100318637A1 (en) | 2005-06-21 | 2010-08-24 | Process for optimizing software components for an enterprise resource planning (erp) application sap on multiprocessor servers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/157,395 US7805706B1 (en) | 2005-06-21 | 2005-06-21 | Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/862,229 Division US20100318637A1 (en) | 2005-06-21 | 2010-08-24 | Process for optimizing software components for an enterprise resource planning (erp) application sap on multiprocessor servers |
Publications (1)
Publication Number | Publication Date |
---|---|
US7805706B1 true US7805706B1 (en) | 2010-09-28 |
Family
ID=42753238
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/157,395 Active 2029-04-30 US7805706B1 (en) | 2005-06-21 | 2005-06-21 | Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers |
US12/862,229 Abandoned US20100318637A1 (en) | 2005-06-21 | 2010-08-24 | Process for optimizing software components for an enterprise resource planning (erp) application sap on multiprocessor servers |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/862,229 Abandoned US20100318637A1 (en) | 2005-06-21 | 2010-08-24 | Process for optimizing software components for an enterprise resource planning (erp) application sap on multiprocessor servers |
Country Status (1)
Country | Link |
---|---|
US (2) | US7805706B1 (en) |
Cited By (110)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060230387A1 (en) * | 2005-04-06 | 2006-10-12 | Microsoft Corporation | Memory management configuration |
US20080046859A1 (en) * | 2006-08-18 | 2008-02-21 | Samantha Pineda Velarde | System and method for evaluating adherence to a standardized process |
US20080155137A1 (en) * | 2006-12-22 | 2008-06-26 | Hewlett-Packard Development Company, L.P. | Processing an input/output request on a multiprocessor system |
US20090282175A1 (en) * | 2008-05-07 | 2009-11-12 | Emulex Design & Manufacturing Corporation | System and Method for Enabling Multiple Processors to Share Multiple SAS Wide Ports |
US20090293051A1 (en) * | 2008-05-22 | 2009-11-26 | Fortinet, Inc., A Delaware Corporation | Monitoring and dynamic tuning of target system performance |
US20100198641A1 (en) * | 2009-01-30 | 2010-08-05 | Microsoft Corporation | Ecommerce marketplace integration techniques |
US20100223164A1 (en) * | 2007-06-04 | 2010-09-02 | Fortier Stephane Maxime Francois | Methods and Computer-Readable Media for Enabling Secure Online Transactions With Simplified User Experience |
US20100318637A1 (en) * | 2005-06-21 | 2010-12-16 | Tania Trinh Ly | Process for optimizing software components for an enterprise resource planning (erp) application sap on multiprocessor servers |
US20110153305A1 (en) * | 2009-08-04 | 2011-06-23 | Chang Henry C | Software extensions to a high level description language simulator to provide infrastructure for analog, mixed-signal, RF modeling and verification |
US20110185360A1 (en) * | 2010-01-28 | 2011-07-28 | International Business Machines Corporation | Multiprocessing transaction recovery manager |
US20110295647A1 (en) * | 2008-12-05 | 2011-12-01 | Hisaya Ishibashi | Manufacturing plan drawing-up system and method |
US20120101984A1 (en) * | 2010-10-21 | 2012-04-26 | Unisys Corporation | Method for performance tuning a database |
US20120197961A1 (en) * | 2007-04-13 | 2012-08-02 | Platform Computing Corporation | Method and system for information exchange utilizing an asynchronous persistent store protocol |
US20120210304A1 (en) * | 2009-07-08 | 2012-08-16 | Nec Corporation | Program reconfiguration system and program reconfiguration method |
US20130232238A1 (en) * | 2011-11-04 | 2013-09-05 | International Business Machines Corporation | Mobile device with multiple security domains |
US8578111B2 (en) | 2011-10-11 | 2013-11-05 | Hewlett-Packard Development Company, L.P. | Backup optimization policy table for controlling buffered/un-buffered input/output |
US20140032608A1 (en) * | 2012-07-30 | 2014-01-30 | Gregory P. Comeau | Database adapter |
US20140201714A1 (en) * | 2013-01-11 | 2014-07-17 | Tata Consultancy Services Limited | Evaluating performance maturity level of an application |
US8806155B2 (en) * | 2009-02-19 | 2014-08-12 | Micron Technology, Inc. | Methods and apparatus for designating or using data status indicators |
US8832210B2 (en) * | 2011-08-30 | 2014-09-09 | Oracle International Corporation | Online monitoring for customer service |
US9026553B2 (en) * | 2012-11-29 | 2015-05-05 | Unisys Corporation | Data expanse viewer for database systems |
US20150135170A1 (en) * | 2013-11-14 | 2015-05-14 | Google Inc. | Methods and Systems for Providing Compatibility of Applications with Multiple Versions of an Operating System |
US20150161047A1 (en) * | 2013-12-10 | 2015-06-11 | Samsung Electronics Co., Ltd. | Multi-core cpu system for adjusting l2 cache character, method thereof, and devices having the same |
US20150169322A1 (en) * | 2006-03-31 | 2015-06-18 | Ebay Inc. | Distributed parallel build system |
US20150355927A1 (en) * | 2014-06-04 | 2015-12-10 | Yahoo! Inc. | Automatic virtual machine resizing to optimize resource availability |
US9229850B1 (en) * | 2009-06-30 | 2016-01-05 | Emc Corporation | Mapping data storage and virtual machines |
US9256467B1 (en) * | 2014-11-11 | 2016-02-09 | Amazon Technologies, Inc. | System for managing and scheduling containers |
US9348625B2 (en) | 2014-05-23 | 2016-05-24 | Google Inc. | Application access to native and bundled libraries |
US20160147984A1 (en) * | 2014-11-20 | 2016-05-26 | International Business Machines Corporation | Implementing extent granularity authorization initialization processing in capi adapters |
US20160173335A1 (en) * | 2014-12-12 | 2016-06-16 | Freescale Semiconductor, Inc. | Network interface module and a method of changing network configuration parameters within a network device |
US9378228B2 (en) * | 2013-03-08 | 2016-06-28 | Sap Se | Enterprise resource planning running on multiple databases |
US9465667B1 (en) * | 2011-07-15 | 2016-10-11 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
US9563532B1 (en) * | 2011-12-02 | 2017-02-07 | Google Inc. | Allocation of tasks in large scale computing systems |
US9582659B2 (en) | 2014-11-20 | 2017-02-28 | International Business Machines Corporation | Implementing extent granularity authorization and deauthorization processing in CAPI adapters |
US9582651B2 (en) | 2014-11-20 | 2017-02-28 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US9594710B2 (en) | 2014-11-20 | 2017-03-14 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US9645884B2 (en) * | 2005-12-23 | 2017-05-09 | Intel Corporation | Performing a cyclic redundancy checksum operation responsive to a user-level instruction |
US9690622B1 (en) | 2015-08-24 | 2017-06-27 | Amazon Technologies, Inc. | Stateless instance backed mobile devices |
US9697370B2 (en) | 2014-11-20 | 2017-07-04 | International Business Machines Corporation | Implementing and processing extent granularity authorization mechanism in CAPI adapters |
EP3143510A4 (en) * | 2014-05-20 | 2017-12-27 | Krystallize Technologies, Inc. | Load generation application and cloud computing benchmarking |
US9858443B2 (en) | 2014-11-20 | 2018-01-02 | International Business Machines Corporation | Implementing block device extent granularity authorization model processing in CAPI adapters |
US9886435B2 (en) | 2014-12-24 | 2018-02-06 | Sap Se | Pseudo internal numbering mechanism |
US9916233B1 (en) | 2015-03-27 | 2018-03-13 | Amazon Technologies, Inc. | Using containers for update deployment |
US9928141B1 (en) | 2015-09-21 | 2018-03-27 | Amazon Technologies, Inc. | Exploiting variable media size in grid encoded data storage systems |
US9940474B1 (en) | 2015-09-29 | 2018-04-10 | Amazon Technologies, Inc. | Techniques and systems for data segregation in data storage systems |
US9959167B1 (en) | 2015-07-01 | 2018-05-01 | Amazon Technologies, Inc. | Rebundling grid encoded data storage systems |
US9998539B1 (en) | 2015-07-01 | 2018-06-12 | Amazon Technologies, Inc. | Non-parity in grid encoded data storage systems |
US9998150B1 (en) | 2015-06-16 | 2018-06-12 | Amazon Technologies, Inc. | Layered data redundancy coding techniques for layer-local data recovery |
US10002247B2 (en) | 2015-12-18 | 2018-06-19 | Amazon Technologies, Inc. | Software container registry container image deployment |
US10032032B2 (en) | 2015-12-18 | 2018-07-24 | Amazon Technologies, Inc. | Software container registry inspection |
US10061668B1 (en) | 2016-03-28 | 2018-08-28 | Amazon Technologies, Inc. | Local storage clustering for redundancy coded data storage system |
US10067848B2 (en) * | 2016-07-27 | 2018-09-04 | Facebook, Inc. | Methods and systems for benchmarking web browser performance |
US10069869B2 (en) | 2016-05-17 | 2018-09-04 | Amazon Technologies, Inc. | Versatile autoscaling |
US10089176B1 (en) | 2015-07-01 | 2018-10-02 | Amazon Technologies, Inc. | Incremental updates of grid encoded data storage systems |
US10102065B1 (en) | 2015-12-17 | 2018-10-16 | Amazon Technologies, Inc. | Localized failure mode decorrelation in redundancy encoded data storage systems |
US10110442B2 (en) | 2015-02-20 | 2018-10-23 | Microsoft Technology Licensing, Llc | Hierarchical data surfacing configurations with automatic updates |
US10108819B1 (en) | 2015-07-01 | 2018-10-23 | Amazon Technologies, Inc. | Cross-datacenter extension of grid encoded data storage systems |
US10127105B1 (en) | 2015-12-17 | 2018-11-13 | Amazon Technologies, Inc. | Techniques for extending grids in data storage systems |
US10133599B1 (en) | 2011-11-04 | 2018-11-20 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
US10162704B1 (en) | 2015-07-01 | 2018-12-25 | Amazon Technologies, Inc. | Grid encoded data storage systems for efficient data repair |
US10176012B2 (en) | 2014-12-12 | 2019-01-08 | Nxp Usa, Inc. | Method and apparatus for implementing deterministic response frame transmission |
US10180912B1 (en) | 2015-12-17 | 2019-01-15 | Amazon Technologies, Inc. | Techniques and systems for data segregation in redundancy coded data storage systems |
US10198311B1 (en) | 2015-07-01 | 2019-02-05 | Amazon Technologies, Inc. | Cross-datacenter validation of grid encoded data storage systems |
US10235402B1 (en) | 2015-12-17 | 2019-03-19 | Amazon Technologies, Inc. | Techniques for combining grid-encoded data storage systems |
US10248793B1 (en) | 2015-12-16 | 2019-04-02 | Amazon Technologies, Inc. | Techniques and systems for durable encryption and deletion in data storage systems |
US10261782B2 (en) | 2015-12-18 | 2019-04-16 | Amazon Technologies, Inc. | Software container registry service |
US10270476B1 (en) | 2015-06-16 | 2019-04-23 | Amazon Technologies, Inc. | Failure mode-sensitive layered redundancy coding techniques |
US10270475B1 (en) | 2015-06-16 | 2019-04-23 | Amazon Technologies, Inc. | Layered redundancy coding for encoded parity data |
US10298259B1 (en) | 2015-06-16 | 2019-05-21 | Amazon Technologies, Inc. | Multi-layered data redundancy coding techniques |
US10296764B1 (en) | 2016-11-18 | 2019-05-21 | Amazon Technologies, Inc. | Verifiable cryptographically secured ledgers for human resource systems |
US10318353B2 (en) | 2011-07-15 | 2019-06-11 | Mark Henrik Sandstrom | Concurrent program execution optimization |
US10324790B1 (en) | 2015-12-17 | 2019-06-18 | Amazon Technologies, Inc. | Flexible data storage device mapping for data storage systems |
US10332190B1 (en) * | 2004-01-30 | 2019-06-25 | Jpmorgan Chase Bank, N.A. | System and method for trade payment exchange |
US10366062B1 (en) | 2016-03-28 | 2019-07-30 | Amazon Technologies, Inc. | Cycled clustering for redundancy coded data storage systems |
US10394762B1 (en) | 2015-07-01 | 2019-08-27 | Amazon Technologies, Inc. | Determining data redundancy in grid encoded data storage systems |
US10394789B1 (en) | 2015-12-07 | 2019-08-27 | Amazon Technologies, Inc. | Techniques and systems for scalable request handling in data processing systems |
US10409642B1 (en) | 2016-11-22 | 2019-09-10 | Amazon Technologies, Inc. | Customer resource monitoring for versatile scaling service scaling policy recommendations |
US10412022B1 (en) | 2016-10-19 | 2019-09-10 | Amazon Technologies, Inc. | On-premises scaling using a versatile scaling service and an application programming interface management service |
US10437790B1 (en) | 2016-09-28 | 2019-10-08 | Amazon Technologies, Inc. | Contextual optimization for data storage systems |
US10496327B1 (en) | 2016-09-28 | 2019-12-03 | Amazon Technologies, Inc. | Command parallelization for data storage systems |
US10592336B1 (en) | 2016-03-24 | 2020-03-17 | Amazon Technologies, Inc. | Layered indexing for asynchronous retrieval of redundancy coded data |
US20200097146A1 (en) * | 2018-09-21 | 2020-03-26 | Sap Se | Configuration Object Deletion Manager |
US10609122B1 (en) | 2015-06-29 | 2020-03-31 | Amazon Technologies, Inc. | Instance backed building or place |
US10614239B2 (en) | 2016-09-30 | 2020-04-07 | Amazon Technologies, Inc. | Immutable cryptographically secured ledger-backed databases |
US10628352B2 (en) | 2016-07-19 | 2020-04-21 | Nxp Usa, Inc. | Heterogeneous multi-processor device and method of enabling coherent data access within a heterogeneous multi-processor device |
US10642813B1 (en) | 2015-12-14 | 2020-05-05 | Amazon Technologies, Inc. | Techniques and systems for storage and processing of operational data |
US20200150940A1 (en) * | 2018-11-09 | 2020-05-14 | International Business Machines Corporation | Optimization of container image |
US10657097B1 (en) | 2016-09-28 | 2020-05-19 | Amazon Technologies, Inc. | Data payload aggregation for data storage systems |
US10678664B1 (en) | 2016-03-28 | 2020-06-09 | Amazon Technologies, Inc. | Hybridized storage operation for redundancy coded data storage systems |
US10693946B2 (en) | 2014-09-16 | 2020-06-23 | Amazon Technologies, Inc. | Instance backed mobile devices |
US10782990B1 (en) | 2015-11-24 | 2020-09-22 | Amazon Technologies, Inc. | Container telemetry |
US10810157B1 (en) | 2016-09-28 | 2020-10-20 | Amazon Technologies, Inc. | Command aggregation for data storage operations |
US10911404B1 (en) | 2015-08-24 | 2021-02-02 | Amazon Technologies, Inc. | Attribute based authorization |
US10977128B1 (en) | 2015-06-16 | 2021-04-13 | Amazon Technologies, Inc. | Adaptive data loss mitigation for redundancy coding systems |
US11004532B2 (en) * | 2018-06-18 | 2021-05-11 | Teledyne Lecroy, Inc. | Method and system for analyzing traffic data |
US11061969B1 (en) | 2015-06-29 | 2021-07-13 | Amazon Technologies, Inc. | Instance backed mobile devices with multiple instances |
US11140455B1 (en) | 2017-06-09 | 2021-10-05 | Amazon Technologies, Inc. | Video encoder network sandboxing |
US11137980B1 (en) | 2016-09-27 | 2021-10-05 | Amazon Technologies, Inc. | Monotonic time-based data storage |
US11204895B1 (en) | 2016-09-28 | 2021-12-21 | Amazon Technologies, Inc. | Data payload clustering for data storage systems |
US11221887B2 (en) | 2019-03-22 | 2022-01-11 | Amazon Technologies, Inc. | Bin-packing virtual machine workloads using forecasted capacity usage |
US11243794B2 (en) | 2019-03-22 | 2022-02-08 | Amazon Technologies, Inc. | Interactive GUI for bin-packing virtual machine workloads based on predicted availability of compute instances and scheduled use of the compute instances |
US11249810B2 (en) * | 2019-03-22 | 2022-02-15 | Amazon Technologies, Inc. | Coordinated predictive autoscaling of virtualized resource groups |
US11269888B1 (en) | 2016-11-28 | 2022-03-08 | Amazon Technologies, Inc. | Archival data storage for structured data |
US11281624B1 (en) | 2016-09-28 | 2022-03-22 | Amazon Technologies, Inc. | Client-based batching of data payload |
US20220215447A1 (en) * | 2021-01-07 | 2022-07-07 | Stripe, Inc. | Invoice Numbering |
US11386060B1 (en) | 2015-09-23 | 2022-07-12 | Amazon Technologies, Inc. | Techniques for verifiably processing data in distributed computing systems |
US20220237697A1 (en) * | 2009-12-10 | 2022-07-28 | Royal Bank Of Canada | Synchronized processing of data by networked computing resources |
US20220318214A1 (en) * | 2021-03-30 | 2022-10-06 | International Business Machines Corporation | Virtual database resource usage |
CN115358728A (en) * | 2022-10-20 | 2022-11-18 | 杭州上杰云服科技有限公司 | ERP data processing method based on cloud computing |
US11669365B1 (en) | 2019-08-26 | 2023-06-06 | Amazon Technologies, Inc. | Task pool for managed compute instances |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8453013B1 (en) * | 2008-07-09 | 2013-05-28 | Google Inc | System-hang recovery mechanisms for distributed systems |
US8762794B2 (en) * | 2010-11-18 | 2014-06-24 | Nec Laboratories America, Inc. | Cross-layer system architecture design |
US8875148B2 (en) | 2011-06-14 | 2014-10-28 | International Business Machines Corporation | Product-specific system resource allocation within a single operating system instance |
US9009444B1 (en) * | 2012-09-29 | 2015-04-14 | Emc Corporation | System and method for LUN control management |
US8656134B2 (en) * | 2012-11-08 | 2014-02-18 | Concurix Corporation | Optimized memory configuration deployed on executing code |
US8656135B2 (en) * | 2012-11-08 | 2014-02-18 | Concurix Corporation | Optimized memory configuration deployed prior to execution |
US9612949B2 (en) * | 2013-06-13 | 2017-04-04 | Arm Limited | Memory allocation in a multi-core processing system based on a threshold amount of memory |
US9773218B2 (en) * | 2013-07-30 | 2017-09-26 | Red Hat, Inc. | Segmented business process engine |
US10095286B2 (en) | 2014-05-30 | 2018-10-09 | Apple Inc. | Thermally adaptive quality-of-service |
US10203746B2 (en) * | 2014-05-30 | 2019-02-12 | Apple Inc. | Thermal mitigation using selective task modulation |
WO2016011494A1 (en) * | 2014-07-25 | 2016-01-28 | Ip Key Pty Ltd | Frameworks and methodologies configured to enable integration of booking and access control for service providers |
US11138537B2 (en) * | 2014-09-17 | 2021-10-05 | International Business Machines Corporation | Data volume-based server hardware sizing using edge case analysis |
US10678568B2 (en) * | 2017-11-02 | 2020-06-09 | International Business Machines Corporation | System resource allocation in respect of display interfaces |
JP7087585B2 (en) * | 2018-03-30 | 2022-06-21 | 日本電気株式会社 | Information processing equipment, control methods, and programs |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030046130A1 (en) * | 2001-08-24 | 2003-03-06 | Golightly Robert S. | System and method for real-time enterprise optimization |
US6601192B1 (en) | 1999-08-31 | 2003-07-29 | Accenture Llp | Assertion component in environment services patterns |
US20030196062A1 (en) | 2002-04-12 | 2003-10-16 | International Business Machines Coporation | Memory balancing and optimization services |
US20060047794A1 (en) * | 2004-09-02 | 2006-03-02 | Microsoft Corporation | Application of genetic algorithms to computer system tuning |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6738847B1 (en) * | 2000-11-10 | 2004-05-18 | Unisys Corporation | Method for assigning a multiplicity of interrupt vectors in a symmetric multi-processor computing environment |
US7805706B1 (en) * | 2005-06-21 | 2010-09-28 | Unisys Corporation | Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers |
-
2005
- 2005-06-21 US US11/157,395 patent/US7805706B1/en active Active
-
2010
- 2010-08-24 US US12/862,229 patent/US20100318637A1/en not_active Abandoned
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6601192B1 (en) | 1999-08-31 | 2003-07-29 | Accenture Llp | Assertion component in environment services patterns |
US20030046130A1 (en) * | 2001-08-24 | 2003-03-06 | Golightly Robert S. | System and method for real-time enterprise optimization |
US20030196062A1 (en) | 2002-04-12 | 2003-10-16 | International Business Machines Coporation | Memory balancing and optimization services |
US20060047794A1 (en) * | 2004-09-02 | 2006-03-02 | Microsoft Corporation | Application of genetic algorithms to computer system tuning |
Non-Patent Citations (2)
Title |
---|
Kemper et al., "Performance Tuning for SAP R/3", Bulletin of the Technical Committee on Data Engineering, IEEE, Jun. 1999, p. 32-39. * |
Unisys e-@action Enterprise Server Software Release Notes for Release 3.1 on CS7101; Unisys, Jun. 2001, 19pg. * |
Cited By (201)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10332190B1 (en) * | 2004-01-30 | 2019-06-25 | Jpmorgan Chase Bank, N.A. | System and method for trade payment exchange |
US8713524B2 (en) * | 2005-04-06 | 2014-04-29 | Microsoft Corporation | Memory management configuration |
US20060230387A1 (en) * | 2005-04-06 | 2006-10-12 | Microsoft Corporation | Memory management configuration |
US20100318637A1 (en) * | 2005-06-21 | 2010-12-16 | Tania Trinh Ly | Process for optimizing software components for an enterprise resource planning (erp) application sap on multiprocessor servers |
US11048579B2 (en) | 2005-12-23 | 2021-06-29 | Intel Corporation | Performing a cyclic redundancy checksum operation responsive to a user-level instruction |
US9645884B2 (en) * | 2005-12-23 | 2017-05-09 | Intel Corporation | Performing a cyclic redundancy checksum operation responsive to a user-level instruction |
US10379938B2 (en) | 2005-12-23 | 2019-08-13 | Intel Corporation | Performing a cyclic redundancy checksum operation responsive to a user-level instruction |
US11899530B2 (en) | 2005-12-23 | 2024-02-13 | Intel Corporation | Performing a cyclic redundancy checksum operation responsive to a user-level instruction |
US10048961B2 (en) | 2006-03-31 | 2018-08-14 | Ebay Inc. | Distributed parallel build system |
US11106459B2 (en) | 2006-03-31 | 2021-08-31 | Ebay Inc. | Distributed parallel build system |
US20150169322A1 (en) * | 2006-03-31 | 2015-06-18 | Ebay Inc. | Distributed parallel build system |
US10620943B2 (en) | 2006-03-31 | 2020-04-14 | Ebay Inc. | Distributed parallel build system |
US9529589B2 (en) * | 2006-03-31 | 2016-12-27 | Ebay Inc. | Distributed parallel build system |
US8635599B2 (en) * | 2006-08-18 | 2014-01-21 | International Business Machines Corporation | System and method for evaluating adherence to a standardized process |
US20080046859A1 (en) * | 2006-08-18 | 2008-02-21 | Samantha Pineda Velarde | System and method for evaluating adherence to a standardized process |
US8402172B2 (en) * | 2006-12-22 | 2013-03-19 | Hewlett-Packard Development Company, L.P. | Processing an input/output request on a multiprocessor system |
US20080155137A1 (en) * | 2006-12-22 | 2008-06-26 | Hewlett-Packard Development Company, L.P. | Processing an input/output request on a multiprocessor system |
US20120197961A1 (en) * | 2007-04-13 | 2012-08-02 | Platform Computing Corporation | Method and system for information exchange utilizing an asynchronous persistent store protocol |
US9407715B2 (en) * | 2007-04-13 | 2016-08-02 | International Business Machines Corporation | Method and system for information exchange utilizing an asynchronous persistent store protocol |
US9967360B2 (en) | 2007-04-13 | 2018-05-08 | International Business Machines Corporation | Method and system for information exchange utilizing an asynchronous persistent store protocol |
US10180958B2 (en) * | 2007-06-04 | 2019-01-15 | Bce Inc. | Methods and computer-readable media for enabling secure online transactions with simplified user experience |
US20100223164A1 (en) * | 2007-06-04 | 2010-09-02 | Fortier Stephane Maxime Francois | Methods and Computer-Readable Media for Enabling Secure Online Transactions With Simplified User Experience |
US8417858B2 (en) * | 2008-05-07 | 2013-04-09 | Emulex Design & Manufacturing Corporation | System and method for enabling multiple processors to share multiple SAS wide ports |
US20090282175A1 (en) * | 2008-05-07 | 2009-11-12 | Emulex Design & Manufacturing Corporation | System and Method for Enabling Multiple Processors to Share Multiple SAS Wide Ports |
US20090293051A1 (en) * | 2008-05-22 | 2009-11-26 | Fortinet, Inc., A Delaware Corporation | Monitoring and dynamic tuning of target system performance |
US20110295647A1 (en) * | 2008-12-05 | 2011-12-01 | Hisaya Ishibashi | Manufacturing plan drawing-up system and method |
US20100198641A1 (en) * | 2009-01-30 | 2010-08-05 | Microsoft Corporation | Ecommerce marketplace integration techniques |
US8442865B2 (en) | 2009-01-30 | 2013-05-14 | Microsoft Corporation | Ecommerce marketplace integration techniques |
US8036942B2 (en) * | 2009-01-30 | 2011-10-11 | Microsoft Corporation | Ecommerce marketplace integration techniques |
US8806155B2 (en) * | 2009-02-19 | 2014-08-12 | Micron Technology, Inc. | Methods and apparatus for designating or using data status indicators |
US9229850B1 (en) * | 2009-06-30 | 2016-01-05 | Emc Corporation | Mapping data storage and virtual machines |
US20120210304A1 (en) * | 2009-07-08 | 2012-08-16 | Nec Corporation | Program reconfiguration system and program reconfiguration method |
US20110153305A1 (en) * | 2009-08-04 | 2011-06-23 | Chang Henry C | Software extensions to a high level description language simulator to provide infrastructure for analog, mixed-signal, RF modeling and verification |
US8666720B2 (en) * | 2009-08-04 | 2014-03-04 | Henry Chung-herng Chang | Software extensions to a high level description language simulator to provide infrastructure for analog, mixed-signal, RF modeling and verification |
US20220237697A1 (en) * | 2009-12-10 | 2022-07-28 | Royal Bank Of Canada | Synchronized processing of data by networked computing resources |
US11776054B2 (en) * | 2009-12-10 | 2023-10-03 | Royal Bank Of Canada | Synchronized processing of data by networked computing resources |
US20110185360A1 (en) * | 2010-01-28 | 2011-07-28 | International Business Machines Corporation | Multiprocessing transaction recovery manager |
US9086911B2 (en) | 2010-01-28 | 2015-07-21 | International Business Machines Corporation | Multiprocessing transaction recovery manager |
US8499298B2 (en) * | 2010-01-28 | 2013-07-30 | International Business Machines Corporation | Multiprocessing transaction recovery manager |
US20120101984A1 (en) * | 2010-10-21 | 2012-04-26 | Unisys Corporation | Method for performance tuning a database |
US8341181B2 (en) * | 2010-10-21 | 2012-12-25 | Unisys Corporation | Method for performance tuning a database |
US10514953B2 (en) | 2011-07-15 | 2019-12-24 | Throughputer, Inc. | Systems and methods for managing resource allocation and concurrent program execution on an array of processor cores |
US10318353B2 (en) | 2011-07-15 | 2019-06-11 | Mark Henrik Sandstrom | Concurrent program execution optimization |
US9465667B1 (en) * | 2011-07-15 | 2016-10-11 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
US8832210B2 (en) * | 2011-08-30 | 2014-09-09 | Oracle International Corporation | Online monitoring for customer service |
US8578111B2 (en) | 2011-10-11 | 2013-11-05 | Hewlett-Packard Development Company, L.P. | Backup optimization policy table for controlling buffered/un-buffered input/output |
US9842207B2 (en) * | 2011-11-04 | 2017-12-12 | International Business Machines Corporation | Mobile device with multiple security domains |
US20160026790A1 (en) * | 2011-11-04 | 2016-01-28 | International Business Machines Corporation | Mobile device with multiple security domains |
US20130232238A1 (en) * | 2011-11-04 | 2013-09-05 | International Business Machines Corporation | Mobile device with multiple security domains |
US11150948B1 (en) | 2011-11-04 | 2021-10-19 | Throughputer, Inc. | Managing programmable logic-based processing unit allocation on a parallel data processing platform |
US10133599B1 (en) | 2011-11-04 | 2018-11-20 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
US10430242B2 (en) | 2011-11-04 | 2019-10-01 | Throughputer, Inc. | Task switching and inter-task communications for coordination of applications executing on a multi-user parallel processing architecture |
US10963306B2 (en) | 2011-11-04 | 2021-03-30 | Throughputer, Inc. | Managing resource sharing in a multi-core data processing fabric |
US10133600B2 (en) | 2011-11-04 | 2018-11-20 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
US10310902B2 (en) | 2011-11-04 | 2019-06-04 | Mark Henrik Sandstrom | System and method for input data load adaptive parallel processing |
US20210303354A1 (en) | 2011-11-04 | 2021-09-30 | Throughputer, Inc. | Managing resource sharing in a multi-core data processing fabric |
US11928508B2 (en) | 2011-11-04 | 2024-03-12 | Throughputer, Inc. | Responding to application demand in a system that uses programmable logic components |
US10310901B2 (en) | 2011-11-04 | 2019-06-04 | Mark Henrik Sandstrom | System and method for input data load adaptive parallel processing |
US10437644B2 (en) | 2011-11-04 | 2019-10-08 | Throughputer, Inc. | Task switching and inter-task communications for coordination of applications executing on a multi-user parallel processing architecture |
US10789099B1 (en) | 2011-11-04 | 2020-09-29 | Throughputer, Inc. | Task switching and inter-task communications for coordination of applications executing on a multi-user parallel processing architecture |
US9152223B2 (en) * | 2011-11-04 | 2015-10-06 | International Business Machines Corporation | Mobile device with multiple security domains |
US10620998B2 (en) | 2011-11-04 | 2020-04-14 | Throughputer, Inc. | Task switching and inter-task communications for coordination of applications executing on a multi-user parallel processing architecture |
US9563532B1 (en) * | 2011-12-02 | 2017-02-07 | Google Inc. | Allocation of tasks in large scale computing systems |
US10061615B2 (en) | 2012-06-08 | 2018-08-28 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
USRE47677E1 (en) | 2012-06-08 | 2019-10-29 | Throughputer, Inc. | Prioritizing instances of programs for execution based on input data availability |
USRE47945E1 (en) * | 2012-06-08 | 2020-04-14 | Throughputer, Inc. | Application load adaptive multi-stage parallel data processing architecture |
US20140032608A1 (en) * | 2012-07-30 | 2014-01-30 | Gregory P. Comeau | Database adapter |
US10942778B2 (en) | 2012-11-23 | 2021-03-09 | Throughputer, Inc. | Concurrent program execution optimization |
US9026553B2 (en) * | 2012-11-29 | 2015-05-05 | Unisys Corporation | Data expanse viewer for database systems |
US9158663B2 (en) * | 2013-01-11 | 2015-10-13 | Tata Consultancy Services Limited | Evaluating performance maturity level of an application |
US20140201714A1 (en) * | 2013-01-11 | 2014-07-17 | Tata Consultancy Services Limited | Evaluating performance maturity level of an application |
US9378228B2 (en) * | 2013-03-08 | 2016-06-28 | Sap Se | Enterprise resource planning running on multiple databases |
US11687374B2 (en) | 2013-08-23 | 2023-06-27 | Throughputer, Inc. | Configurable logic platform with reconfigurable processing circuitry |
US11915055B2 (en) | 2013-08-23 | 2024-02-27 | Throughputer, Inc. | Configurable logic platform with reconfigurable processing circuitry |
US11816505B2 (en) | 2013-08-23 | 2023-11-14 | Throughputer, Inc. | Configurable logic platform with reconfigurable processing circuitry |
US11188388B2 (en) | 2013-08-23 | 2021-11-30 | Throughputer, Inc. | Concurrent program execution optimization |
US11036556B1 (en) | 2013-08-23 | 2021-06-15 | Throughputer, Inc. | Concurrent program execution optimization |
US11347556B2 (en) | 2013-08-23 | 2022-05-31 | Throughputer, Inc. | Configurable logic platform with reconfigurable processing circuitry |
US11500682B1 (en) | 2013-08-23 | 2022-11-15 | Throughputer, Inc. | Configurable logic platform with reconfigurable processing circuitry |
US11385934B2 (en) | 2013-08-23 | 2022-07-12 | Throughputer, Inc. | Configurable logic platform with reconfigurable processing circuitry |
US9058193B2 (en) * | 2013-11-14 | 2015-06-16 | Google Inc. | Methods and systems for providing compatibility of applications with multiple versions of an operating system |
US20150135170A1 (en) * | 2013-11-14 | 2015-05-14 | Google Inc. | Methods and Systems for Providing Compatibility of Applications with Multiple Versions of an Operating System |
US20150161047A1 (en) * | 2013-12-10 | 2015-06-11 | Samsung Electronics Co., Ltd. | Multi-core cpu system for adjusting l2 cache character, method thereof, and devices having the same |
US9817759B2 (en) * | 2013-12-10 | 2017-11-14 | Samsung Electronics Co., Ltd. | Multi-core CPU system for adjusting L2 cache character, method thereof, and devices having the same |
EP3143510A4 (en) * | 2014-05-20 | 2017-12-27 | Krystallize Technologies, Inc. | Load generation application and cloud computing benchmarking |
US9348625B2 (en) | 2014-05-23 | 2016-05-24 | Google Inc. | Application access to native and bundled libraries |
US20150355927A1 (en) * | 2014-06-04 | 2015-12-10 | Yahoo! Inc. | Automatic virtual machine resizing to optimize resource availability |
US10693946B2 (en) | 2014-09-16 | 2020-06-23 | Amazon Technologies, Inc. | Instance backed mobile devices |
US11314541B2 (en) | 2014-11-11 | 2022-04-26 | Amazon Technologies, Inc. | System for managing and scheduling containers |
US9256467B1 (en) * | 2014-11-11 | 2016-02-09 | Amazon Technologies, Inc. | System for managing and scheduling containers |
US10838756B2 (en) | 2014-11-11 | 2020-11-17 | Amazon Technologies, Inc. | System for managing and scheduling containers |
US9996380B2 (en) | 2014-11-11 | 2018-06-12 | Amazon Technologies, Inc. | System for managing and scheduling containers |
US11669362B2 (en) | 2014-11-11 | 2023-06-06 | Amazon Technologies, Inc. | System for managing and scheduling containers |
US9594710B2 (en) | 2014-11-20 | 2017-03-14 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US9767261B2 (en) * | 2014-11-20 | 2017-09-19 | International Business Machines Corporation | Implementing extent granularity authorization initialization processing in CAPI adapters |
US9898599B2 (en) | 2014-11-20 | 2018-02-20 | International Business Machines Corporation | Implementing extent granularity authorization and deauthorization processing in CAPI adapters |
US9891852B2 (en) | 2014-11-20 | 2018-02-13 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US10043028B2 (en) | 2014-11-20 | 2018-08-07 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US9886575B2 (en) | 2014-11-20 | 2018-02-06 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US9858443B2 (en) | 2014-11-20 | 2018-01-02 | International Business Machines Corporation | Implementing block device extent granularity authorization model processing in CAPI adapters |
US9904795B2 (en) | 2014-11-20 | 2018-02-27 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US10169605B2 (en) | 2014-11-20 | 2019-01-01 | International Business Machines Corporation | Implementing block device extent granularity authorization model processing in CAPI adapters |
US10013572B2 (en) | 2014-11-20 | 2018-07-03 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US9911000B2 (en) | 2014-11-20 | 2018-03-06 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US9582651B2 (en) | 2014-11-20 | 2017-02-28 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US10055156B2 (en) | 2014-11-20 | 2018-08-21 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US10055574B2 (en) | 2014-11-20 | 2018-08-21 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US9710624B2 (en) | 2014-11-20 | 2017-07-18 | International Business Machines Corporation | Implementing extent granularity authorization initialization processing in CAPI adapters |
US9703972B2 (en) | 2014-11-20 | 2017-07-11 | International Business Machines Corporation | Implementing and processing extent granularity authorization mechanism in CAPI adapters |
US10055573B2 (en) | 2014-11-20 | 2018-08-21 | International Business Machines Corporation | Implementing extent granularity authorization and deauthorization processing in CAPI adapters |
US20160147984A1 (en) * | 2014-11-20 | 2016-05-26 | International Business Machines Corporation | Implementing extent granularity authorization initialization processing in capi adapters |
US10055606B2 (en) | 2014-11-20 | 2018-08-21 | International Business Machines Corporation | Implementing block device extent granularity authorization model processing in CAPI adapters |
US9582659B2 (en) | 2014-11-20 | 2017-02-28 | International Business Machines Corporation | Implementing extent granularity authorization and deauthorization processing in CAPI adapters |
US9697370B2 (en) | 2014-11-20 | 2017-07-04 | International Business Machines Corporation | Implementing and processing extent granularity authorization mechanism in CAPI adapters |
US9600428B2 (en) | 2014-11-20 | 2017-03-21 | International Business Machines Corporation | Implementing extent granularity authorization command flow processing in CAPI adapters |
US9600642B2 (en) | 2014-11-20 | 2017-03-21 | International Business Machines Corporation | Implementing extent granularity authorization processing in CAPI adapters |
US9600654B2 (en) | 2014-11-20 | 2017-03-21 | International Business Machines Corporation | Implementing extent granularity authorization and deauthorization processing in CAPI adapters |
US20160173335A1 (en) * | 2014-12-12 | 2016-06-16 | Freescale Semiconductor, Inc. | Network interface module and a method of changing network configuration parameters within a network device |
US10505757B2 (en) * | 2014-12-12 | 2019-12-10 | Nxp Usa, Inc. | Network interface module and a method of changing network configuration parameters within a network device |
US10176012B2 (en) | 2014-12-12 | 2019-01-08 | Nxp Usa, Inc. | Method and apparatus for implementing deterministic response frame transmission |
US9886435B2 (en) | 2014-12-24 | 2018-02-06 | Sap Se | Pseudo internal numbering mechanism |
US10110442B2 (en) | 2015-02-20 | 2018-10-23 | Microsoft Technology Licensing, Llc | Hierarchical data surfacing configurations with automatic updates |
US11061812B2 (en) | 2015-03-27 | 2021-07-13 | Amazon Technologies, Inc. | Using containers for update deployment |
US9916233B1 (en) | 2015-03-27 | 2018-03-13 | Amazon Technologies, Inc. | Using containers for update deployment |
US10298259B1 (en) | 2015-06-16 | 2019-05-21 | Amazon Technologies, Inc. | Multi-layered data redundancy coding techniques |
US10270475B1 (en) | 2015-06-16 | 2019-04-23 | Amazon Technologies, Inc. | Layered redundancy coding for encoded parity data |
US10270476B1 (en) | 2015-06-16 | 2019-04-23 | Amazon Technologies, Inc. | Failure mode-sensitive layered redundancy coding techniques |
US9998150B1 (en) | 2015-06-16 | 2018-06-12 | Amazon Technologies, Inc. | Layered data redundancy coding techniques for layer-local data recovery |
US10977128B1 (en) | 2015-06-16 | 2021-04-13 | Amazon Technologies, Inc. | Adaptive data loss mitigation for redundancy coding systems |
US11061969B1 (en) | 2015-06-29 | 2021-07-13 | Amazon Technologies, Inc. | Instance backed mobile devices with multiple instances |
US10609122B1 (en) | 2015-06-29 | 2020-03-31 | Amazon Technologies, Inc. | Instance backed building or place |
US10162704B1 (en) | 2015-07-01 | 2018-12-25 | Amazon Technologies, Inc. | Grid encoded data storage systems for efficient data repair |
US10198311B1 (en) | 2015-07-01 | 2019-02-05 | Amazon Technologies, Inc. | Cross-datacenter validation of grid encoded data storage systems |
US10089176B1 (en) | 2015-07-01 | 2018-10-02 | Amazon Technologies, Inc. | Incremental updates of grid encoded data storage systems |
US10108819B1 (en) | 2015-07-01 | 2018-10-23 | Amazon Technologies, Inc. | Cross-datacenter extension of grid encoded data storage systems |
US10394762B1 (en) | 2015-07-01 | 2019-08-27 | Amazon Technologies, Inc. | Determining data redundancy in grid encoded data storage systems |
US9998539B1 (en) | 2015-07-01 | 2018-06-12 | Amazon Technologies, Inc. | Non-parity in grid encoded data storage systems |
US9959167B1 (en) | 2015-07-01 | 2018-05-01 | Amazon Technologies, Inc. | Rebundling grid encoded data storage systems |
US10459764B2 (en) | 2015-08-24 | 2019-10-29 | Amazon Technologies, Inc. | Stateless instance backed mobile devices |
US9690622B1 (en) | 2015-08-24 | 2017-06-27 | Amazon Technologies, Inc. | Stateless instance backed mobile devices |
US10911404B1 (en) | 2015-08-24 | 2021-02-02 | Amazon Technologies, Inc. | Attribute based authorization |
US10853142B2 (en) | 2015-08-24 | 2020-12-01 | Amazon Technologies, Inc. | Stateless instance backed mobile devices |
US9928141B1 (en) | 2015-09-21 | 2018-03-27 | Amazon Technologies, Inc. | Exploiting variable media size in grid encoded data storage systems |
US11386060B1 (en) | 2015-09-23 | 2022-07-12 | Amazon Technologies, Inc. | Techniques for verifiably processing data in distributed computing systems |
US9940474B1 (en) | 2015-09-29 | 2018-04-10 | Amazon Technologies, Inc. | Techniques and systems for data segregation in data storage systems |
US10782990B1 (en) | 2015-11-24 | 2020-09-22 | Amazon Technologies, Inc. | Container telemetry |
US10394789B1 (en) | 2015-12-07 | 2019-08-27 | Amazon Technologies, Inc. | Techniques and systems for scalable request handling in data processing systems |
US11537587B2 (en) | 2015-12-14 | 2022-12-27 | Amazon Technologies, Inc. | Techniques and systems for storage and processing of operational data |
US10642813B1 (en) | 2015-12-14 | 2020-05-05 | Amazon Technologies, Inc. | Techniques and systems for storage and processing of operational data |
US10248793B1 (en) | 2015-12-16 | 2019-04-02 | Amazon Technologies, Inc. | Techniques and systems for durable encryption and deletion in data storage systems |
US10324790B1 (en) | 2015-12-17 | 2019-06-18 | Amazon Technologies, Inc. | Flexible data storage device mapping for data storage systems |
US10102065B1 (en) | 2015-12-17 | 2018-10-16 | Amazon Technologies, Inc. | Localized failure mode decorrelation in redundancy encoded data storage systems |
US10235402B1 (en) | 2015-12-17 | 2019-03-19 | Amazon Technologies, Inc. | Techniques for combining grid-encoded data storage systems |
US10180912B1 (en) | 2015-12-17 | 2019-01-15 | Amazon Technologies, Inc. | Techniques and systems for data segregation in redundancy coded data storage systems |
US10127105B1 (en) | 2015-12-17 | 2018-11-13 | Amazon Technologies, Inc. | Techniques for extending grids in data storage systems |
US10725775B2 (en) | 2015-12-18 | 2020-07-28 | Amazon Technologies, Inc. | Software container registry service |
US10002247B2 (en) | 2015-12-18 | 2018-06-19 | Amazon Technologies, Inc. | Software container registry container image deployment |
US11487530B2 (en) | 2015-12-18 | 2022-11-01 | Amazon Technologies, Inc. | Software container registry service |
US10261782B2 (en) | 2015-12-18 | 2019-04-16 | Amazon Technologies, Inc. | Software container registry service |
US11789723B2 (en) | 2015-12-18 | 2023-10-17 | Amazon Technologies, Inc. | Software container registry service |
US10032032B2 (en) | 2015-12-18 | 2018-07-24 | Amazon Technologies, Inc. | Software container registry inspection |
US10592336B1 (en) | 2016-03-24 | 2020-03-17 | Amazon Technologies, Inc. | Layered indexing for asynchronous retrieval of redundancy coded data |
US11113161B2 (en) | 2016-03-28 | 2021-09-07 | Amazon Technologies, Inc. | Local storage clustering for redundancy coded data storage system |
US10678664B1 (en) | 2016-03-28 | 2020-06-09 | Amazon Technologies, Inc. | Hybridized storage operation for redundancy coded data storage systems |
US10366062B1 (en) | 2016-03-28 | 2019-07-30 | Amazon Technologies, Inc. | Cycled clustering for redundancy coded data storage systems |
US10061668B1 (en) | 2016-03-28 | 2018-08-28 | Amazon Technologies, Inc. | Local storage clustering for redundancy coded data storage system |
US10979436B2 (en) | 2016-05-17 | 2021-04-13 | Amazon Technologies, Inc. | Versatile autoscaling for containers |
US10135837B2 (en) | 2016-05-17 | 2018-11-20 | Amazon Technologies, Inc. | Versatile autoscaling for containers |
US10397240B2 (en) | 2016-05-17 | 2019-08-27 | Amazon Technologies, Inc. | Versatile autoscaling for containers |
US10069869B2 (en) | 2016-05-17 | 2018-09-04 | Amazon Technologies, Inc. | Versatile autoscaling |
US10628352B2 (en) | 2016-07-19 | 2020-04-21 | Nxp Usa, Inc. | Heterogeneous multi-processor device and method of enabling coherent data access within a heterogeneous multi-processor device |
US10067848B2 (en) * | 2016-07-27 | 2018-09-04 | Facebook, Inc. | Methods and systems for benchmarking web browser performance |
US11137980B1 (en) | 2016-09-27 | 2021-10-05 | Amazon Technologies, Inc. | Monotonic time-based data storage |
US10657097B1 (en) | 2016-09-28 | 2020-05-19 | Amazon Technologies, Inc. | Data payload aggregation for data storage systems |
US11281624B1 (en) | 2016-09-28 | 2022-03-22 | Amazon Technologies, Inc. | Client-based batching of data payload |
US11204895B1 (en) | 2016-09-28 | 2021-12-21 | Amazon Technologies, Inc. | Data payload clustering for data storage systems |
US10810157B1 (en) | 2016-09-28 | 2020-10-20 | Amazon Technologies, Inc. | Command aggregation for data storage operations |
US10496327B1 (en) | 2016-09-28 | 2019-12-03 | Amazon Technologies, Inc. | Command parallelization for data storage systems |
US10437790B1 (en) | 2016-09-28 | 2019-10-08 | Amazon Technologies, Inc. | Contextual optimization for data storage systems |
US10614239B2 (en) | 2016-09-30 | 2020-04-07 | Amazon Technologies, Inc. | Immutable cryptographically secured ledger-backed databases |
US10412022B1 (en) | 2016-10-19 | 2019-09-10 | Amazon Technologies, Inc. | On-premises scaling using a versatile scaling service and an application programming interface management service |
US10296764B1 (en) | 2016-11-18 | 2019-05-21 | Amazon Technologies, Inc. | Verifiable cryptographically secured ledgers for human resource systems |
US10409642B1 (en) | 2016-11-22 | 2019-09-10 | Amazon Technologies, Inc. | Customer resource monitoring for versatile scaling service scaling policy recommendations |
US11347549B2 (en) | 2016-11-22 | 2022-05-31 | Amazon Technologies, Inc. | Customer resource monitoring for versatile scaling service scaling policy recommendations |
US11269888B1 (en) | 2016-11-28 | 2022-03-08 | Amazon Technologies, Inc. | Archival data storage for structured data |
US11140455B1 (en) | 2017-06-09 | 2021-10-05 | Amazon Technologies, Inc. | Video encoder network sandboxing |
US11004532B2 (en) * | 2018-06-18 | 2021-05-11 | Teledyne Lecroy, Inc. | Method and system for analyzing traffic data |
US11175802B2 (en) * | 2018-09-21 | 2021-11-16 | Sap Se | Configuration object deletion manager |
US20200097146A1 (en) * | 2018-09-21 | 2020-03-26 | Sap Se | Configuration Object Deletion Manager |
US20200150940A1 (en) * | 2018-11-09 | 2020-05-14 | International Business Machines Corporation | Optimization of container image |
US10838702B2 (en) * | 2018-11-09 | 2020-11-17 | International Business Machines Corporation | Analyzing and optimizing container images in cloud computing |
US11221887B2 (en) | 2019-03-22 | 2022-01-11 | Amazon Technologies, Inc. | Bin-packing virtual machine workloads using forecasted capacity usage |
US11249810B2 (en) * | 2019-03-22 | 2022-02-15 | Amazon Technologies, Inc. | Coordinated predictive autoscaling of virtualized resource groups |
US11243794B2 (en) | 2019-03-22 | 2022-02-08 | Amazon Technologies, Inc. | Interactive GUI for bin-packing virtual machine workloads based on predicted availability of compute instances and scheduled use of the compute instances |
US11669365B1 (en) | 2019-08-26 | 2023-06-06 | Amazon Technologies, Inc. | Task pool for managed compute instances |
US11763359B2 (en) * | 2021-01-07 | 2023-09-19 | Stripe, Inc. | Invoice numbering |
US20220215447A1 (en) * | 2021-01-07 | 2022-07-07 | Stripe, Inc. | Invoice Numbering |
US11681672B2 (en) * | 2021-03-30 | 2023-06-20 | International Business Machines Corporation | Virtual database resource usage |
US20220318214A1 (en) * | 2021-03-30 | 2022-10-06 | International Business Machines Corporation | Virtual database resource usage |
CN115358728B (en) * | 2022-10-20 | 2023-01-24 | 杭州上杰云服科技有限公司 | ERP data processing method based on cloud computing |
CN115358728A (en) * | 2022-10-20 | 2022-11-18 | 杭州上杰云服科技有限公司 | ERP data processing method based on cloud computing |
Also Published As
Publication number | Publication date |
---|---|
US20100318637A1 (en) | 2010-12-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7805706B1 (en) | Process for optimizing software components for an enterprise resource planning (ERP) application SAP on multiprocessor servers | |
US7222343B2 (en) | Dynamic allocation of computer resources based on thread type | |
US8230434B2 (en) | Entitlement management system, method and program product for resource allocation among micro-partitions | |
US10108654B2 (en) | Workload balancing in a distributed database | |
US7376770B2 (en) | System and method for virtual adapter resource allocation matrix that defines the amount of resources of a physical I/O adapter | |
US6871264B2 (en) | System and method for dynamic processor core and cache partitioning on large-scale multithreaded, multiprocessor integrated circuits | |
US8752055B2 (en) | Method of managing resources within a set of processes | |
US8656077B2 (en) | Apparatus, method and system for aggregating computing resources | |
US7464191B2 (en) | System and method for host initialization for an adapter that supports virtualization | |
JP5159884B2 (en) | Network adapter resource allocation between logical partitions | |
US20060193327A1 (en) | System and method for providing quality of service in a virtual adapter | |
US20170031699A1 (en) | Multiprocessing Within a Storage Array System Executing Controller Firmware Designed for a Uniprocessor Environment | |
US20090100249A1 (en) | Method and apparatus for allocating architectural register resources among threads in a multi-threaded microprocessor core | |
US20080071755A1 (en) | Re-allocation of resources for query execution in partitions | |
US7167854B2 (en) | Database control method | |
US20120072624A1 (en) | Numa i/o framework | |
US10409519B2 (en) | Interface device, and computer system including interface device | |
US11556391B2 (en) | CPU utilization for service level I/O scheduling | |
US8578383B2 (en) | Intelligent pre-started job affinity for non-uniform memory access computer system | |
US8533163B2 (en) | Database offload processing | |
US20080010290A1 (en) | Application offload processing | |
US10824640B1 (en) | Framework for scheduling concurrent replication cycles | |
Singhal et al. | OpenFAM: Programming disaggregated memory | |
Korotkevitch et al. | System Troubleshooting | |
WO2015145595A1 (en) | Computer system and method for managing computer system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: UNISYS CORPORATION, PENNSYLVANIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LY, TANIA TRINH;PRADITPHOLLERT, KULWIPA;REEL/FRAME:016743/0594 Effective date: 20050621 |
|
AS | Assignment |
Owner name: CITIBANK, N.A., NEW YORK Free format text: SECURITY AGREEMENT;ASSIGNORS:UNISYS CORPORATION;UNISYS HOLDING CORPORATION;REEL/FRAME:018003/0001 Effective date: 20060531 |
|
AS | Assignment |
Owner name: UNISYS CORPORATION, PENNSYLVANIA Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:023086/0255 Effective date: 20090601 Owner name: UNISYS HOLDING CORPORATION, DELAWARE Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:CITIBANK, N.A.;REEL/FRAME:023086/0255 Effective date: 20090601 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
AS | Assignment |
Owner name: DEUTSCHE BANK NATIONAL TRUST COMPANY, NEW JERSEY Free format text: SECURITY AGREEMENT;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:025227/0391 Effective date: 20101102 |
|
AS | Assignment |
Owner name: GENERAL ELECTRIC CAPITAL CORPORATION, AS AGENT, IL Free format text: SECURITY AGREEMENT;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:026509/0001 Effective date: 20110623 |
|
AS | Assignment |
Owner name: UNISYS CORPORATION, PENNSYLVANIA Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:DEUTSCHE BANK TRUST COMPANY;REEL/FRAME:030004/0619 Effective date: 20121127 |
|
AS | Assignment |
Owner name: UNISYS CORPORATION, PENNSYLVANIA Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:DEUTSCHE BANK TRUST COMPANY AMERICAS, AS COLLATERAL TRUSTEE;REEL/FRAME:030082/0545 Effective date: 20121127 |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
AS | Assignment |
Owner name: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS COLLATE Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:042354/0001 Effective date: 20170417 Owner name: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS COLLATERAL TRUSTEE, NEW YORK Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:042354/0001 Effective date: 20170417 |
|
AS | Assignment |
Owner name: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT, ILLINOIS Free format text: SECURITY INTEREST;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:044144/0081 Effective date: 20171005 Owner name: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT Free format text: SECURITY INTEREST;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:044144/0081 Effective date: 20171005 |
|
AS | Assignment |
Owner name: UNISYS CORPORATION, PENNSYLVANIA Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:WELLS FARGO BANK, NATIONAL ASSOCIATION (SUCCESSOR TO GENERAL ELECTRIC CAPITAL CORPORATION);REEL/FRAME:044416/0358 Effective date: 20171005 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552) Year of fee payment: 8 |
|
AS | Assignment |
Owner name: UNISYS CORPORATION, PENNSYLVANIA Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:WELLS FARGO BANK, NATIONAL ASSOCIATION;REEL/FRAME:054231/0496 Effective date: 20200319 |
|
AS | Assignment |
Owner name: WELLS FARGO BANK, NATIONAL ASSOCIATION, MINNESOTA Free format text: SECURITY INTEREST;ASSIGNOR:UNISYS CORPORATION;REEL/FRAME:054481/0865 Effective date: 20201029 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |